Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full behavioral burden. It usefully discloses a hard prerequisite ('Requires IBM SPSS Statistics to be installed') and that post-hoc testing is conditional, but says nothing about error behavior, whether the dependent must be scale, or how the factor is treated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short, front-loaded sentences with no filler; the core operation leads and the prerequisite is placed last. Efficient, though it spends words on the optional feature while omitting required-parameter context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained. The prerequisite is covered, but for a 4-parameter tool with 0% schema description coverage the definition leaves the required inputs and input-data expectations undocumented.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the description explains only the post_hoc parameter by giving example values (TUKEY, BONFERRONI, LSD), which the schema lacks. The three required parameters (file_path, dependent, factor) receive no explanation in either the schema or the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and statistical resource ('Run SPSS one-way ANOVA (ONEWAY)'), which lets an agent distinguish it from siblings like spss_repeated_measures_anova, spss_manova, and spss_glm_univariate. It does not name those siblings explicitly, so differentiation relies on the agent's knowledge of the procedures.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no when-to-use guidance or exclusions relative to the many alternative ANOVA/GLM tools in the sibling list. It only notes that post-hoc tests are optional, which is a capability note rather than routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are supplied, so the description carries the full burden. It does disclose the rendering path (GGRAPH + OMS) and that the result is an exported image file in one of three formats, which signals a file-writing side effect. It does not say where the file is written or returned, whether a dataset must already be open, or anything about the SPSS backend dependency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One tightly packed sentence with the resource and formats front-loaded and no filler. The 'via GGRAPH + OMS' clause is implementation detail but short and arguably informative about how SPPS renders it.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A 10-parameter, no-annotation tool needs substantially more description than this; the output schema covers the return value, but the meaning of seven parameters and the destination of the exported file are undocumented. An agent would have to guess at data_file handling and sizing semantics before calling it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 10 parameters, so the description must compensate and it only partly does. It adds meaning for x (time/ordinal) and y, and hints at image format via 'PNG/TIFF/EMF', but says nothing about data_file, dpi, width_px/height_px, title, x_label, or y_label.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Export') and a specific resource ('area chart') plus the accepted output formats (PNG/TIFF/EMF), which is enough for an agent to know this produces an image rather than a statistic. It does not explicitly differentiate itself from near neighbours like spss_chart_line or spss_chart_bar, so the sibling routing is left slightly to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: 'y against a time/ordinal x variable' tells the agent the data shape this chart suits, which functions as an implicit when-to-use condition. There is no explicit guidance on when to pick an area chart over spss_chart_line or spss_chart_bar, and no prerequisites or exclusions are named.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden; it does disclose the output artifact types and the underlying GGRAPH + OMS IMAGE mechanism, which is genuinely useful context. However, it omits whether the call writes a file to disk and returns a path, where the image lands, whether existing files are overwritten, and whether an SPSS session must already be active.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence with no filler, front-loading the action and the output formats before the plotting semantics. Every clause earns its place and nothing is buried.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter tool with no annotations, the description is too thin: only 2 required params and the stat choice are addressed. The presence of an output schema excuses it from explaining return values, but the numerous optional formatting and data-source parameters remain unexplained, leaving the agent unable to judge how to set them.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 11 parameters, so the description must compensate and largely does not. It conveys the category/value pairing and the stat choice, but adds nothing about data_file (versus an active dataset), dpi, width_px/height_px units, or how title/x_label/y_label are applied.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb (export) and resource (bar chart), plus the plot's semantics: categorical variable vs. mean/sum of a continuous variable, in named image formats and via GGRAPH + OMS IMAGE. It implicitly distinguishes itself from spss_chart_bar_error by not mentioning error bars, but never names that sibling, so differentiation is left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to choose this over spss_chart_bar_error, spss_chart_histogram, or the other chart siblings. The agent must infer from the plot description alone that this is the plain aggregated bar chart with no error bars, and nothing states prerequisites such as an active dataset or prior file load.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden, yet it only names the underlying mechanism (GGRAPH + OMS). It does not say whether the chart is written to a file or returned inline, whether it operates on the active dataset or a named file, whether OMS routing changes session output state, or what permissions/state effects exist.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with no padding; the artifact and formats come first. 'via GGRAPH + OMS' is implementation jargon that adds little for an agent choosing the tool, but it is brief.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter tool with zero schema coverage and no annotations, the description is far too thin. An output schema exists so return values need not be explained, but the input semantics, dataset source, and side effects are all missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 11 parameters, so the description must compensate and largely fails. It only implicitly touches ci (confidence-interval error bars) and image_format (PNG/TIFF/EMF); required parameters category and value, plus data_file, dpi, width_px, height_px, title, x_label and y_label, are left with no added meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (export) and a well-defined artifact: a bar chart of category means with confidence-interval error bars, plus supported formats (PNG/TIFF/EMF). This differentiates it reasonably well from spss_chart_bar and spss_chart_errorbar, though it never explicitly contrasts itself with those siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance at all. With close siblings like spss_chart_bar (plain bars) and spss_chart_errorbar (error bars) in the list, the description should say which situation selects this combined means-plus-CI chart, but it gives no conditions or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are supplied, so the description carries the full behavioral burden. 'Export' implies a file write, but the description never says where the file lands, what its name will be, whether existing files are overwritten, or whether an active SPSS session/data file is required. The GGRAPH + OMS mention is an implementation detail that does not help an agent anticipate side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences with the main action front-loaded and no filler. The 'via GGRAPH + OMS' clause is arguably lower-value than missing details like output destination, but it does not bloat the text.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter export tool with no annotations, the description is thin: the file-destination question, the role of data_file, and resolution/size parameters are all unaddressed. The existence of an output schema covers return values, which keeps this from being a 1.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 10 parameters, so the description must compensate and largely does not. It explains only 'variable' (continuous) and 'category' (optional grouping); dpi, width_px, height_px, title, x_label, y_label, and especially data_file are left entirely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Export a publication-ready box-and-whisker plot'), names the output formats (PNG/TIFF/EMF) and the underlying engine (GGRAPH + OMS). It is clearly distinct from siblings like spss_chart_histogram or spss_chart_scatter, though it never explicitly says so.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Provide a continuous variable and optionally a categorical grouping variable' gives input-level guidance and implies the required continuous-vs-categorical data shape. There is no when-to-use/when-not guidance relative to other chart siblings, and no mention of prerequisites such as whether a dataset must already be loaded or what data_file does.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden and leaves major gaps: where the exported file is written, whether existing files are overwritten, whether SPSS must be running, and what side effects GGRAPH/OMS execution has. Mentioning the GGRAPH + OMS pipeline is mildly informative but does not substitute for operational behavior disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence that front-loads the deliverable and enumerates formats and statistical content without wasted words. The GGRAPH + OMS implementation detail is arguably extra, but it is compact and informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter export tool with no annotations, the description should explain output destination, required data context, and the roles of the dimension and resolution parameters. The presence of an output schema relieves the need to describe return values, but the operational gaps remain substantial.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 11 parameters, so the description must compensate. It implies the meaning of 'ci' (confidence-interval whiskers) and lists the image_format values, but says nothing about category, value, data_file, dpi, width_px, height_px, title, or axis labels.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: exporting an error bar chart showing mean with confidence-interval whiskers per category, with explicit output formats (PNG/TIFF/EMF). It distinguishes itself from nearby chart siblings like spss_chart_bar_error only implicitly, but the chart type and statistical content are clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description never says when to choose this over spss_chart_bar_error, spss_chart_boxplot, or spss_chart_line, nor does it mention prerequisites such as an active SPSS session or required data_file. The agent must infer usage from the chart type alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden; it does disclose the export mechanism, supported formats, and that a chart file path is returned. It omits important behavior such as where files are written, whether existing files are overwritten, and whether an active SPSS session or dataset is required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences with the action and output format front-loaded and no filler. The GGRAPH/OMS IMAGE jargon is minor noise but adds implementation context rather than padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Although an output schema exists so return values need not be spelled out, a 9-parameter charting tool with zero schema coverage and no annotations needs far more guidance than two sentences. The description does not explain how sizing, DPI, labels, or data_file affect the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 9 parameters, so the description must compensate, yet it only clarifies that "variable" should be continuous. Nothing is said about dpi, width_px/height_px, image_format, title/x_label/y_label, or the role of data_file, leaving most inputs unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Export a publication-ready histogram") plus the underlying mechanism (GGRAPH + OMS IMAGE) and output formats. It does not differentiate itself from the very similar sibling spss_chart_histogram_density, so an agent must guess which to pick.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Provide the continuous variable" hints at the input requirement but gives no when-to-use context, no exclusions, and no mention of the near-identical spss_chart_histogram_density or other chart siblings. The agent is left to infer selection criteria entirely.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It usefully discloses the implementation path (GGRAPH + OMS) and the output format options, which signals this is a file-producing export rather than an in-session plot. However, it never states where the file is written, whether an existing file is overwritten, or what happens if the variable is non-continuous — meaningful gaps for a write-to-disk tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with no redundant wording; the primary output description is front-loaded and the required-input constraint follows. Slightly terse for a 9-parameter tool, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A return/output schema exists so return values need not be explained, but for a 9-parameter file-export tool with zero annotation coverage the description is too thin. It does not explain dataset selection (data_file), sizing/DPI controls, or the on-disk destination, so an agent cannot call it confidently beyond the minimum required variable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 9 parameters, so the description must compensate and largely does not. It clarifies only that 'variable' must be continuous and echoes the three image formats already enumerated in the schema, leaving dpi, width_px, height_px, title, x_label, y_label, and data_file completely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb (renders/exports) and a specific artifact: a histogram overlaid with a normal density curve, in named formats (PNG/TIFF/EMF). It implicitly separates itself from sibling spss_chart_spss_chart_histogram-style plain histogram tools via the density-curve overlay, but never names the sibling or states the distinction explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The clause 'Provide a variable' conveys one clear precondition: the target variable must be continuous. There is no guidance on when to choose this over the plain histogram sibling, no mention of prerequisites such as an active dataset or whether data_file must be supplied, and no exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full burden, yet it only discloses the output formats. It says nothing about where a file is written, whether an existing file is overwritten, what happens if data_file is omitted, or what 'Export' means in terms of side effects — significant gaps for a tool that produces a file artifact.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short, front-loaded sentences with no filler; the artifact and format come first and required inputs second. Brevity is achieved, though at the cost of omitting necessary detail elsewhere.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter charting/export tool with zero schema description coverage and no annotations, the description is far too thin. An output schema exists so return values need not be explained, but the missing parameter meaning and file-writing behavior leave the definition incomplete for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 10 parameters, and the description covers only time, status, and group. Critical parameters like 'event' (presumably the event/censoring code) and 'data_file' are left entirely unexplained, so an agent cannot infer their semantics from the text or schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and artifact ('Export a publication-ready Kaplan-Meier survival curve') and the underlying procedure ('via the KM procedure'), which clearly separates it from analysis siblings like spss_kaplan_meier. It stops short of naming any sibling tool explicitly, so an agent must still infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Provide time and status variables; group is optional' gives minimal input guidance but no when-to-use versus spss_kaplan_meier or the other chart tools, and no exclusions or prerequisites. Usage is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full behavioral burden. It does disclose the implementation (GGRAPH + OMS IMAGE) and that a file path is returned, but it says nothing about where the file is written, whether an existing file is overwritten, whether an active SPSS session/data file is required, or how image_format/format tradeoffs behave.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no filler, front-loading the action and output formats before the minimal input requirement and return value. Nothing in the text is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so the return value needn't be explained, yet the description covers only 2 of 10 parameters and omits the critical question of output file location for an export tool. For a 10-parameter export operation with zero schema coverage and no annotations, this is materially incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 10 parameters, so the description must compensate and largely does not. It adds meaning only for x ('time/ordinal') and y, leaving dpi, width_px, height_px, data_file, title, x_label, y_label and image_format entirely to infer from bare names and defaults.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Export a publication-ready line chart') plus the output formats, which separates it from sibling chart tools like spss_chart_scatter or spss_chart_bar. It does not explicitly name a sibling or state the condition that selects a line chart over those, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The clause 'Provide the x (time/ordinal) and y variables' implies the intended usage context (a continuous series plotted against time or an ordinal axis), which is genuine guidance. There is no explicit when-to-use/when-not statement and no routing to alternative chart tools for non-sequential data, so usage is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It does disclose useful behavior: a normal Q-Q plot is produced via PPLOT and captured through the OMS chart pipeline in PNG/TIFF/EMF, which hints at the SPSS-side mechanics. It omits where the file lands, whether it overwrites, and what dataset context is assumed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loaded with the deliverable and scoped by the pipeline note. No filler, no repetition of the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Weakness is not here: an output schema exists so return values need no explanation, and the sentence covers output type, format options, and the procedure used. The remaining gap is the undocumented data_file/dpi/size parameters and the missing routing hint versus normality_outliers, which the input schema does not supply.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 7 parameters. The description names the image formats (matching the one enum) and constrains 'variable' to a continuous variable, but says nothing about dpi, width_px, height_px, title, or data_file — leaving most parameters undocumented anywhere.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Export'), a specific artifact ('normal Q-Q plot of a continuous variable'), the underlying procedure (PPLOT) and the output formats. It is clearly distinguishable from the chart siblings (histogram, scatter, boxplot, errorbar, etc.) which all target different plot types.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance is given. The most relevant routing decision — visual Q-Q plot (this tool) versus spss_normality_outliers (numeric normality testing) — is never addressed, nor is any prerequisite or exclusion stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are supplied, so the description carries the full disclosure burden. It does add real value by naming the return value (a chart file path for direct submission) and the rendering pipeline (GGRAPH + OMS IMAGE), but it omits that the call writes a file to disk, whether an existing file is overwritten, and which dataset is charted when data_file is omitted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two dense sentences, front-loaded with purpose and output formats. 'Via GGRAPH + OMS IMAGE' is mildly implementation-flavored but does signal the SPSS-specific rendering path; nothing is padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the return value needs no explanation, yet the description spends a clause on it while leaving ten parameters and an absent annotation set unaddressed. For a charting tool that resolves its own dataset and writes to disk, the missing data_file and file-write semantics are significant gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 10 parameters, and the description only touches x, y, and implicitly the format enum. Seven parameters — dpi, title, x_label, y_label, width_px, height_px, and especially data_file — receive no meaning from either the schema or the prose, so an agent cannot tell what data_file does or whether it is needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — export a scatter plot — plus the concrete output formats (PNG/TIFF/EMF). An agent can distinguish it from spss_chart_histogram or spss_chart_line by chart type, though no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The only usage guidance is 'Provide x and y variables,' which is a restatement of the required parameters rather than a when-to-use rule. Nothing says when a scatter plot is preferable to the other chart siblings, nor what state the session must be in beforehand.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden and does disclose the key behavioral insight: whether SPSS is fully installed or the server is in file-only mode, which fundamentally changes what other tools can do. It does not explicitly state that the call is side-effect-free or local, leaving a small gap, but the returned information is well described.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences, front-loaded with the core status-check purpose and then the when-to-call guidance. Every phrase earns its place without repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given a zero-parameter tool, no annotations, and an output schema that documents return values, the description covers everything needed: what is checked, why it matters (installed vs file-only), and when to call it. Nothing required for correct invocation is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the baseline is 4. The empty schema means there is no parameter semantics to document, and the description correctly focuses on return content instead.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Check the SPSS MCP server status') and enumerates exactly what is reported: available capabilities, installed vs file-only mode, SPSS path, library versions, and configuration. This distinguishes it from all sibling tools, which perform analysis rather than environment introspection.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'Call this first to understand what tools are available,' giving a clear invocation context. No alternative sibling competes for this purpose, so no exclusion guidance is needed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It usefully discloses the external dependency ('Requires IBM SPSS Statistics to be installed'), but says nothing about whether this executes syntax that mutates the session, what permissions are needed, or how execution failures surface.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the core action. Efficient, though the dependency note could be positioned after the capability details for better priority ordering.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value explanation is not required. For a fairly complex 6-parameter statistical tool with zero schema documentation, however, the description leaves method/measure selection and variable input expectations unexplained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for 6 parameters. The description gestures at 'multiple linkage methods and distance measures' (method, measure) and the dendrogram flag, but adds no enum semantics, no explanation of file_path/variables/id_variable, and no indication of defaults or required fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: 'Run hierarchical cluster analysis with dendrogram.' This clearly identifies the statistical procedure and distinguishes it from siblings like spss_twostep_cluster and spss_factor, though it never names the differentiating sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to choose hierarchical clustering over spss_twostep_cluster, nor prerequisites such as variable type requirements or when linkage/distance choices should be varied. The reader must infer usage entirely.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the SPSS installation requirement, but does not say whether the tool modifies the source file, writes a new variable to disk, or how reverse coding and min_valid interact with the computation. Side effects and failure behavior are left unstated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with no wasted words, front-loading the core action before the prerequisite. Both sentences earn their place and the text is easy to scan.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 8 parameters, 0% schema description coverage, no annotations, and a composite-scoring operation that likely mutates data, the description is too thin. Because an output schema exists, return values need not be explained, but critical operational details about parameter meaning and side effects are missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, but it only clarifies method (SUM or MEAN), reverse coding, and minimum valid item count. It does not explain file_path, new_variable, items, reverse_items, or the reverse_min/reverse_max pair, leaving most of the 8 parameters undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Compute a scale score (SUM or MEAN) from multiple item variables') and adds scope details like reverse coding and minimum valid item count. It does not explicitly distinguish itself from siblings such as spss_reliability_alpha or spss_run_syntax, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use guidance, no exclusions, and no named alternatives. The only contextual note is the prerequisite that IBM SPSS Statistics must be installed, which is not usage guidance. An agent must infer when this tool is preferred over other SPSS procedures.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses the external SPSS dependency, which is genuinely useful, but says nothing about runtime behavior, side effects, error handling, or whether the underlying data is modified. For a computation tool with zero annotation coverage this is thin.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, front-loaded with the action and the method choice, with no filler. Every clause earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described, but with no usage guidance and 0% parameter documentation the agent lacks enough to invoke this correctly beyond guessing at file_path/variables semantics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across four parameters. The description mentions Pearson/Spearman, but that merely restates the enum already present in the schema; file_path, variables, and two_tailed receive no explanation, so the description fails to compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: run SPSS CORRELATIONS and compute a Pearson or Spearman correlation matrix. This clearly distinguishes it from regression, crosstabs, and other statistical siblings in the list, though it does not name an alternative explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The only guidance is the prerequisite that IBM SPSS Statistics must be installed. There is no indication of when to choose correlations over, say, regression or crosstabs, nor any exclusion conditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It notes the SPSS dependency and mentions feature support (time-dependent covariates, stratification, diagnostics), but says nothing about whether files are read or written, side effects of save_survival, or runtime/permission constraints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three compact sentences, front-loaded with the core purpose, then capabilities, then the environment requirement. No filler, though it is arguably too terse given the parameter surface.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be described, but for a 9-parameter statistical tool with zero annotation coverage and zero schema descriptions, the description is far too thin on parameter meaning, prerequisites, and behavioral expectations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% with 9 parameters and none documented in the schema. The description only loosely gestures at strata ('stratification') and diagnostics, leaving file_path, time_variable, status_variable, status_event_value, predictors, method, categorical, and save_survival entirely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Run Cox proportional hazards regression for survival analysis'), which clearly separates it from sibling tools like spss_logistic_regression and spss_kaplan_meier. It does not explicitly name an alternative, but the method name is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to choose this over spss_kaplan_meier (non-parametric survival) or spss_logistic_regression, nor any stated prerequisites beyond SPSS being installed. The agent must infer the use case from the method name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It usefully discloses the external dependency ('Requires IBM SPSS Statistics to be installed') and the optional outputs (chi-square, row/column percentages), but it does not state whether the input file is modified, whether the operation is read-only, or what error conditions look like.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the core action, followed by optional behavior and the prerequisite. Every sentence adds distinct information, and nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described. The description covers the tool's purpose, optional outputs, and dependency, which is largely sufficient for a moderately complex statistical procedure. The main gap is that it does not describe the expected input file format or whether defaults apply.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It explains that row_variable and column_variable are categorical variables and maps include_chisquare, include_row_pct, and include_col_pct to chi-square and percentage outputs. It does not clarify file_path format or that the boolean options default to true, but the core parameter meanings are covered.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Run SPSS CROSSTABS') and resource ('contingency table between two categorical variables'), making the tool's function immediately clear. However, it does not explicitly distinguish itself from statistical siblings such as spss_frequencies or spss_descriptives, which prevents a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the stated scope: use when analyzing two categorical variables. The prerequisite ('Requires IBM SPSS Statistics to be installed') is noted, but there is no explicit guidance on when to choose this over alternatives like spss_frequencies or spss_nonparametric_tests, and no exclusions are stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must carry behavioral disclosure and does add real value: it lists the returned statistics and flags that IBM SPSS Statistics must be installed. It does not cover error behavior, how missing values or non-numeric variables are handled, or whether the call mutates state.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences with the action and scope front-loaded, then output and the environment prerequisite. No filler, though the return-value listing partially duplicates the output schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be restated, and the environment prerequisite is a useful addition. However, with three undocumented parameters and no annotations, the definition leaves gaps an agent would need to resolve before calling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across three parameters. The description hints at the 'statistics' parameter being optional and mentions numeric variables, but 'file_path' (a required parameter) is never explained and no value/format guidance is given for any parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Run SPSS DESCRIPTIVES') scoped to 'numeric variables', which helps an agent distinguish it from frequency/crosstab procedures. It stops short of explicitly naming sibling alternatives like spss_frequencies or spss_file_summary, so differentiation relies on inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'for numeric variables' implies when the tool applies, but there is no explicit when-to-use versus alternatives such as spss_frequencies or spss_file_summary, and no prerequisites about data state. An agent must infer the routing decision.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It discloses the SPSS dependency and mentions stepwise selection and cross-validation, but says nothing about whether save_class/save_scores write files, permission needs, or side effects of a statistical write operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short, front-loaded sentences with no waste. The requirement is stated early and capabilities follow, though there is room for a brief field-level clarification.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter statistical tool with zero schema description coverage and no annotations, the description is far too thin. The output schema covers return values, but parameter meaning and mutation side effects are left undocumented.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 8 parameters, so the description must compensate and does not. It gestures at method (stepwise) and implies groups/predictors, but leaves method enums, priors, group_values, and the save_* flags entirely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Run discriminant analysis') plus the goal ('classify cases into groups'). Discriminant analysis is a distinct method among the statistical siblings, though the description never explicitly distinguishes it from logistic_regression or manova.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no when-to-use guidance, prerequisites for the data, or alternatives among siblings. It only states the environment prerequisite (SPSS installed), not when this method is preferred over others.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the behavioral burden. It usefully states the external dependency (IBM SPSS Statistics required) and lists the result contents (eigenvalues, variance explained, rotated factor matrix), but it omits whether the operation is read-only, any file/output side effects, or performance considerations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the action and result, with the installation prerequisite stated last. No filler, though the return-value sentence is somewhat redundant given the output schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter statistical procedure with no annotations and no schema parameter descriptions, the definition is incomplete. It leaves required parameters (file_path, variables) and n_factors unexplained, so an agent cannot confidently invoke it beyond the method choice.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It hints at the method parameter by naming principal components and principal axis factoring, but it does not explain file_path, variables, n_factors, or the rotation parameter's options and effects.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('Run SPSS FACTOR analysis') and names the two factor extraction methods. It is clear what the tool does, though it does not explicitly distinguish itself from siblings such as spss_cluster_hierarchical or spss_discriminant.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no prerequisites beyond the SPSS installation, and no indication of when to choose this over other dimension-reduction or multivariate siblings. Usage is only implied by the tool name and the mention of factor analysis.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it does disclose one meaningful behavioral trait: the summary is computed locally and does not require an SPSS installation. That is genuinely useful for a suite of SPSS tools that presumably need a backend. It says nothing about error behavior for a missing or malformed file, performance on large .sav files, or any permission requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the operation and its outputs in one dense sentence. The trailing sentence restates 'no SPSS needed' from the parenthetical, which is mild redundancy, but overall it is short and earns most of its space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so enumerating return contents goes beyond necessity, and nothing critical is missing for a single-parameter read tool. Gaps like behavior on unreadable files or large-file performance are minor for this complexity level.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for the single file_path parameter, so the description must compensate. It partially does by implying the argument is a path to an SPSS .sav file, which constrains the expected format, but it adds no guidance on absolute vs relative paths or how the file is located.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Get a summary of an SPSS .sav file') and enumerates exactly what is returned: case count, variable count, variable list, and basic descriptive statistics. It is clear enough to distinguish from deep-analysis siblings, though it does not explicitly contrast with overlapping tools like spss_read_metadata or spss_descriptives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the content list (a fast file-level overview usable before deeper analysis), and the 'computed locally' note hints at when it is appropriate. However, no alternative sibling is named and no condition for choosing this over spss_read_metadata or spss_descriptives is stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It usefully discloses an environment prerequisite ('Requires IBM SPSS Statistics to be installed') and the return shape, but says nothing about error behavior, whether file_path is read-only, or how optional statistics affects execution.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences with no filler, and the core action is front-loaded before the return description and prerequisite. Nothing is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained in depth, and the prerequisite is a useful addition. But with 0% schema coverage and no annotations, the missing explanation of file_path and the absence of any alternative-tool guidance leave notable gaps for a 3-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It partially does: 'one or more variables' clarifies the variables param accepts multiple, and 'optional statistics' flags the third param as non-required. However, file_path is never explained, leaving the most important parameter undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Run SPSS FREQUENCIES on one or more variables') and describes the output ('frequency tables with counts, percentages, and optional statistics'). It does not distinguish itself from close siblings like spss_descriptives or spss_crosstabs, so an agent must infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The implied use case is clear (getting frequency tables for one or more variables), but there is no explicit when-to-use guidance, no exclusions, and no routing toward the very similar spss_descriptives or spss_crosstabs siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It usefully discloses the external dependency ('Requires IBM SPSS Statistics to be installed'), but says nothing about whether files are modified, how save_predicted behaves, or side effects. Partial behavioral context only.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with the core action. No wasted phrasing, though the final sentence is a practical constraint rather than descriptive filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 8 parameters, zero schema descriptions, and no annotations, the description is too thin — the agent gets no help mapping its arguments. The output schema covers return values, but the input side is essentially undocumented.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% — no parameter has any description. The description names distributions (which merely restates the existing enum) and alludes to link functions, but leaves file_path, dependent, predictors, categorical, scale, and save_predicted entirely unexplained. It does not compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a clear verb and resource ('Run generalized linear model (GENLIN)') and characterizes the scope via flexible distribution/link functions. It does not explicitly differentiate from close siblings like spss_glm_univariate, spss_logistic_regression, or spss_genlinmixed, so the agent must infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance or alternatives are given. In a family crowded with regression models (logistic, ordinal, glm_univariate, genlinmixed), the absence of routing hints is a real gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It contributes one operational fact, the SPSS installation requirement, but says nothing about side effects, permissions, convergence behavior, or whether data is modified. With no annotations and a complex statistical operation, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three concise sentences with the core purpose front-loaded. The capability note and installation prerequisite each add distinct value. It is efficient, though it could be slightly more informative without becoming bloated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex 7-parameter statistical tool with no schema descriptions and no annotations, the description is incomplete. It gives purpose and an installation prerequisite, but omits parameter semantics and usage guidance versus related tools like spss_genlin and spss_mixed. The output schema covers return values, but invocation details remain underspecified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description provides no information about any of the 7 parameters. Terms like file_path, dependent, fixed_effects, random_effects, distribution, link, and subject are not clarified or mapped to their meaning. The description does not compensate for the lack of schema documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Run generalized linear mixed model combining GLM with random effects.' It adds distinguishing scope with 'non-normal outcomes' and 'hierarchical structure,' which helps separate it from spss_genlin and spss_mixed. It does not explicitly name those siblings, so it falls short of full 5-level differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use it: for hierarchical data with non-normal outcomes. It also states the prerequisite that IBM SPSS Statistics must be installed. However, it gives no explicit when-not guidance or alternatives such as spss_genlin or spss_mixed, leaving selection logic largely to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden, and it does convey that the method must be registry-backed and that this is a read-style inspection. However it omits error behavior for unknown method names, and says nothing about the safety/permission profile beyond the implied read-only nature.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences, front-loaded with the action and followed by the use case. Every clause earns its place with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and this is a simple one-parameter read tool. Still, the definition leaves the agent without guidance on valid method identifiers or the relationship to sibling lookup tools, which is the main gap given no annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the single parameter (tool_name) has no description in the schema. The description hints the argument is a registered method name, but it never states the expected format or how to discover valid values (e.g., via spss_list_supported_methods), so it only partially compensates for the gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Get the JSON schema for a registry-backed SPSS method") that an agent can distinguish from siblings like spss_list_supported_methods and spss_get_method_support. It is clear what it returns, though it never explicitly contrasts itself with those adjacent tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear context for when to use it ("before execution", "parameter inspection", "structured orchestration"), so the agent knows this is a pre-flight inspection step. It does not name alternatives or state when not to use it, keeping it just below a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It does disclose the return content categories and 'Get' implies a read-only, side-effect-free lookup, which is useful. It does not state any auth requirements, error behavior on unknown method names, or whether an unknown tool_name returns empty vs. an error.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single efficient sentence with the verb and scope front-loaded and no filler. Slightly dense in its list of returned categories, but every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation. For a simple single-param lookup this is close to adequate, but the lone parameter is undocumented in both schema and description, and there is no sibling routing guidance.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

One required parameter (tool_name) with 0% schema description coverage, and the description never explains it. The phrase 'registry-backed SPSS method' implies tool_name is a registered method identifier, but format, allowed values, and how to discover valid names are left undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Get support metadata for a registry-backed SPSS method') and enumerates the metadata categories returned (command family, support tier, coverage assertions, documentation tags). It is distinguishable from siblings like spss_get_method_schema and spss_list_supported_methods, though the boundary is implied rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this versus spss_list_supported_methods, spss_get_method_schema, or spss_read_metadata. There are no prerequisites or exclusion conditions, leaving the agent to guess from the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden, and it does disclose one useful environmental prerequisite (SPSS installation). It says nothing about side effects such as file mutation or the save_predicted parameter writing new columns, nor about output format or failure modes, leaving meaningful behavioral gaps for a statistical procedure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short, front-loaded sentences with no filler; the core capability leads and the prerequisite trails. Efficiently sized for the information offered, though some brevity comes at the cost of missing parameter detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained. But with zero annotation coverage, zero schema descriptions, and 8 parameters, the description is not complete enough for reliable invocation – it omits argument semantics and any sibling differentiation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for 8 parameters, so the description must compensate. It loosely maps to emmeans, posthoc/posthoc_method, and factors ('factorial designs'), but leaves file_path, dependent, covariates, and save_predicted completely undocumented in both schema and description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Run univariate general linear model (GLM) with factorial designs') and names the capabilities it covers (EMMs, contrasts, post-hoc). It is distinguishable from multivariate siblings like spss_manova, though it never explicitly contrasts itself with spss_anova or spss_genlin, which an agent could easily confuse it with.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implied usage is present – factorial designs plus EMMs/contrasts/post-hoc signal when the tool is appropriate, and it notes the prerequisite that IBM SPSS Statistics must be installed. However, it names no alternative sibling (spss_anova, spss_genlin, spss_mixed) or the conditions that would route an agent elsewhere.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It usefully discloses the mechanism (pandas + pyreadstat) and the default output location ('saves the .sav file next to the CSV'), but it omits key side-effect details such as overwrite behavior, error handling, and any permissions or validation requirements for a file-writing tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose and uses three efficient sentences. The second sentence is a useful usage comparison rather than fluff, though it has a slight marketing tone; overall it is well-structured and not bloated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given five parameters, no annotations, and 0% schema description coverage, the description is incomplete. It covers the conversion purpose and output location, but fails to explain key parameters like encoding, delimiter, and column_labels, and does not address overwrite or error behavior, so an agent must guess about important call details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description only partially compensates. It explains the default behavior of output_path ('saves the .sav file next to the CSV by default, or to a custom output_path') but says nothing about encoding, delimiter, column_labels, or even the required csv_path, leaving four of five parameters undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: 'Convert a CSV file to SPSS .sav format directly using pandas + pyreadstat.' It also distinguishes the tool from sibling operations by noting it bypasses the SPSS engine and requires no IBM SPSS installation, so an agent can tell it apart from spss_run_syntax or analysis tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives a clear alternative and context: 'Much faster than going through SPSS syntax because it bypasses the SPSS engine entirely.' This implicitly tells the agent to use this tool for CSV-to-SAV conversion instead of relying on SPSS syntax, but it does not explicitly state when not to use the tool or other alternatives among the siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It usefully states a dependency ('Requires IBM SPSS Statistics to be installed') and that survival curves are produced, but says nothing about permissions, computational cost, failure modes for invalid data, or how mutation-like behavior is handled.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three compact sentences, front-loaded with the core action before the dependency note. No filler, though the brevity here reflects under-specification rather than disciplined economy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described. However, for a 7-parameter analytical tool with 0% schema coverage and zero annotations, the description is materially incomplete: an agent cannot tell what value status_event_value expects or what strata/percentiles do.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 7 parameters, so the description must compensate yet it adds almost nothing. Only 'log-rank test' loosely maps to compare_method and 'compares groups' loosely maps to strata; the required time_variable, status_variable, and status_event_value, plus percentiles, are entirely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Run Kaplan-Meier survival analysis with log-rank test,' which is a distinct statistical method. It clearly distinguishes itself by naming the method, though it does not explicitly contrast with the nearby sibling spss_cox_regression or spss_chart_km_curve.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description says it 'compares groups' but gives no when-to-use guidance, no prerequisites beyond the SPSS install, and no comparison to comparable siblings like Cox regression or the KM chart tool. A user would have to infer that this performs the analysis whereas spss_chart_km_curve only plots.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden but only implies this is a safe read/discovery operation. It says nothing about recursion behavior, path resolution, permission requirements, or what happens with an empty/invalid directory. The safety profile is inferable but not disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences, zero waste, with the core action front-loaded and the usage hint following. Nothing extraneous.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values needn't be explained, and the purpose is adequately conveyed for a simple listing tool. But both parameters are undocumented and there are no annotations, leaving meaningful gaps around the 'recursive' behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate and largely fails. It implies the directory is a filesystem location but adds no format details (absolute vs relative path), and the 'recursive' parameter is entirely unaddressed in both schema and description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (List) and resource (.sav files in a directory), which is clearly distinct from sibling tools like spss_list_variables or spss_list_supported_methods. It reads well without opening the schema, though it doesn't explicitly name a sibling to differentiate against.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides a concrete when-to-use condition: 'discovering available datasets when the user hasn't specified a file path.' That is real routing context. However, it names no alternatives and gives no when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It implies a safe read-only listing and discloses that returned methods come with schemas, templates, and coverage assertions, but it never states that it is non-mutating, costs nothing, or what the response shape contains—minor gaps for a discovery tool whose output schema covers the return format.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tightly written sentences with the core purpose and the intended use front-loaded, and no filler. The undefined jargon 'cold methods' costs a little clarity but the structure is efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a no-argument listing tool with an output schema, the description needn't explain return values, and it correctly signals the discovery role. The only residual gap is the unexplained 'cold methods' term and the absence of sibling routing, which is minor given the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline of 4 applies. No misleading parameter guidance is present.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('List registry-backed SPSS methods') and hints at the differentiating scope ('available for structured execution'), which separates it from the analysis siblings. However, it doesn't explicitly name or contrast with the closest siblings spss_get_method_schema and spss_get_method_support, so an agent must infer the distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The second sentence gives implied usage ('Use this to discover cold methods...'), which suggests a discovery step before execution. But it offers no explicit when-not guidance and never names alternatives like spss_get_method_schema, so routing between the three method-related tools is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It usefully discloses that SPSS does not need to be installed, and 'List' implies a read-only, side-effect-free operation, but it says nothing about file access errors, encoding, or performance on large .sav files.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the core action, with no filler or redundancy. Every clause contributes information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is a simple read operation with an output schema, so return values need no explanation. The description is nearly sufficient for correct invocation; only the absence of sibling differentiation and error behavior keeps it from being fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the schema supplies no parameter meaning on its own. The description compensates for the 'search' parameter by explaining it acts as an optional filter, and 'from an SPSS .sav file' implies the file_path argument, but neither parameter's format or expected values are specified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'List all variable names and their labels from an SPSS .sav file.' It is clear what the tool returns, but it does not differentiate itself from close siblings like spss_read_metadata or spss_file_summary, which plausibly also surface variable metadata.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description never says when to choose this over spss_read_metadata, spss_read_data, or spss_file_summary. The only conditional content ('Optionally filter by a search term') describes a parameter, not a usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It discloses the supported modeling features and the environment requirement, which is real value, but says nothing about side effects (whether save_predicted writes new variables into the dataset, whether output files are created), permissions, or failure modes for stepwise selection.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short, front-loaded sentences with no filler; the capability statement leads and the environment prerequisite trails. It is efficient, though it stops short of using the remaining space for the parameter guidance this tool actually lacks.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained. But for an 8-parameter statistical procedure with zero schema descriptions, the description leaves the agent without enough information to call it correctly (e.g., accepted values for contrast or print_options, meaning of file_path, behavior of save_predicted).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 8 parameters, so the schema documents nothing. The description only loosely gestures at three of them (stepwise -> method, categorical -> categorical, diagnostics -> print_options); contrast, file_path, dependent, predictors, and save_predicted get no meaning, format, or accepted values, so the agent cannot reliably populate them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource ('Run binary or multinomial logistic regression'), and the 'binary or multinomial' qualifier distinguishes it from the sibling spss_ordinal_regression and from the generic spss_regression. An agent can route to this tool without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It names supported features ('stepwise selection, categorical predictors, and model diagnostics') and states a hard prerequisite ('Requires IBM SPSS Statistics to be installed'), which implies when the tool is usable. However, it never says when to prefer this over spss_regression or spss_ordinal_regression, nor any exclusions or data requirements.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It discloses only the SPSS installation requirement and that both multivariate effects and univariate follow-ups are produced; it omits read-only vs. mutating nature, any permission or resource constraints, and runtime behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences with the core purpose front-loaded and no filler. It is efficient, though slightly under-specified rather than truly concise in the informative sense.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, but for an 8-parameter statistical tool with zero schema description coverage and no annotations the description is far too thin. Critical inputs like method, factors, covariates and range specifications are left entirely undocumented.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 8 parameters, and the description explains none of them. Nothing is said about method (SSTYPE1-4), factors, covariates, factor_ranges, or the print_univariate/print_multivariate toggles, so the agent must guess from parameter names alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Run) and resource (multivariate analysis of variance / MANOVA) plus the key scope qualifier: multiple dependent variables. This implicitly separates it from spss_anova (single DV), but it never names that sibling or the several other ANOVA-family tools, so the distinction must be inferred.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives a prerequisite (SPSS must be installed) but no when-to-use criteria and no alternatives. With spss_anova, spss_glm_univariate and spss_repeated_measures_anova as siblings, the agent gets no guidance on which to pick for a given data shape.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses the analytical method and its components (regression, indirect effect, Sobel test) and a scope limitation (no PROCESS macro), which is meaningful behavioral context. It omits preconditions such as variable type requirements, how missing data is handled, and whether the file must already be loaded, leaving gaps for a mutation-free but assumption-heavy analysis tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core method and outputs, followed by the scope caveat. No filler, no repetition of the tool name or title.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described. But with zero annotations and zero schema coverage, the description should do more to cover invocation preconditions (data loading state, variable measurement level, assumption checks). It is adequate for identifying the method but thin on operational prerequisites.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for all four required parameters, so the description must compensate. The 'X -> M -> Y' notation usefully maps x=independent, mediator=mediator, y=outcome, covering three of four params. file_path is left unexplained, though its intent is inferable from the spss_* family, so compensation is partial rather than complete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific statistical procedure (Baron & Kenny three-step mediation, X -> M -> Y), enumerates the exact output paths (a/b/c/c', indirect effect a*b, Sobel test), and implicitly delineates itself from the sibling spss_moderation by virtue of being mediation rather than moderation. An agent can identify the tool without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The scope exclusion 'Does not bundle the PROCESS macro' is a useful boundary note, effectively routing users who want PROCESS bootstrapping elsewhere. However, it gives no positive when-to-use guidance relative to spss_regression or spss_moderation, and no prerequisites. Usage is only implied through the tool name and method labels.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden, and it only discloses one operational prerequisite ('Requires IBM SPSS Statistics to be installed'). It says nothing about whether the tool writes files, how convergence/failure is handled, what preprocessing the data needs, or roughly what it returns — significant gaps for a 9-parameter modeling tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with the model type, followed by supported structures and the runtime dependency. No filler, though the capability sentence and the installation sentence are the only substantive content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained. But for a 9-parameter statistical tool with zero annotation coverage and zero schema descriptions, the definition leaves too much undefined — no parameter guidance, no usage context, and no behavioral detail beyond the SPSS dependency.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 9 parameters, so the schema documents only names, types, and one enum, leaving the description to compensate — and it largely does not. Terms like 'random effects' and 'repeated measures structures' loosely gesture at random_effects/repeated, but there is nothing on file_path, dependent, fixed_effects, subject, method (REML vs ML), repeated_type, or covtype_random.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Run linear mixed-effects model (multilevel model) with random effects') and names supported structures (nested/crossed, repeated measures). An agent can identify it as the mixed-modeling tool. It does not, however, explicitly route against close siblings like spss_genlinmixed, spss_repeated_measures_anova, or spss_glm_univariate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use or when-not-to-use guidance, and no alternative is named. The capability phrases ('supports nested and crossed random effects') hint at applicable data shapes but never tell the agent when this tool is the right choice over the repeated-measures ANOVA or GENLINMIXED siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden. It does disclose one meaningful trait beyond the schema: that predictors are mean-centred (which differs from a plain regression) and which interaction term it reports. However, it says nothing about data prerequisites (e.g., an SPSS .sav file, variable scale requirements) or failure behavior, leaving notable gaps for an unannotated tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence that specifies the method, the model equation, and the reported statistic with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the method is concisely specified. But with zero annotations and 0% parameter description coverage, the definition omits prerequisites such as the expected file type/path semantics and any data requirements, leaving it only minimally complete for a four-required-parameter analysis tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must define all four parameters. The formula maps X, W, and Y to x, moderator, and y well enough to infer roles, but file_path is never addressed and the string/variable-name nature of the inputs is left implicit. Partial compensation only.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (run), a specific model (mean-centred moderation regression Y ~ X + W + X*W), and the exact output of interest (the interaction term testing W's moderating effect). This clearly distinguishes it from siblings like spss_regression and spss_mediation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The statistical formulation implicitly signals when to use it (testing whether W moderates X→Y), but there is no explicit when-to-use vs when-not guidance and no named alternative such as spss_mediation for indirect-effect questions. Usage is inferable only from the method name and formula.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It discloses only the installation requirement; it says nothing about whether the source file is modified, what happens on invalid variable/group combinations, or any execution constraints. The presence of an output schema covers return values, but mutation and side-effect behavior remain opaque.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences with no filler, and the core capability is front-loaded before the prerequisite. Nothing is wasted, though the brevity is achieved partly by omitting information an agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a five-parameter statistical tool with no annotations, zero schema coverage, and test-specific parameter requirements, the description is too thin. The output schema excuses it from explaining results, but it should at minimum explain the file_path/variables/grouping requirements that differ across the three tests.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and none of the five parameters are explained in the description. It never clarifies that file_path is an .sav path, what 'variables' should contain, or that grouping_variable/group_values are required for Mann-Whitney and Kruskal-Wallis but not Wilcoxon. Only the test_type enum is reflected, indirectly, by the listed test names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific action ('run') and resource (nonparametric tests) and enumerates the three supported tests, matching the test_type enum. It implicitly separates itself from siblings like spss_t_test and spss_anova by labeling the family as nonparametric, though it never names those alternatives explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It states the environment prerequisite (SPSS installed) but gives no when-to-use guidance, no indication of when a nonparametric test is preferable to the parametric siblings (spss_t_test, spss_anova), and no conditions for choosing among the three offered tests. An agent must infer all routing decisions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It usefully discloses an environmental prerequisite ('Requires IBM SPSS Statistics to be installed') and that plots are optional, but it does not state whether the procedure mutates the file, what happens on missing values, or any performance or permissions characteristics.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the action and target, with the prerequisite placed last. No wasted words, though it is slightly sparse given the tool's analytical complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the description covers purpose, the plots option, and the environment requirement. It is nearly complete for an analysis tool, with the main gap being undocumented file_path semantics and no output-shape hint.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It partially does: 'numeric variables' maps to the variables array and 'optional diagnostic plots' maps to the plots flag (consistent with its default of true), but file_path is never mentioned and no format or element-type guidance is given for variables.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Run), procedure (SPSS EXAMINE), and resource (normality and outliers for numeric variables), which is clear and actionable. However, it does not differentiate itself from closely related siblings like spss_descriptives or spss_chart_qqplot, so an agent must infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage by naming the analytical goal (checking normality and outliers) and noting diagnostic plots are optional, but it gives no explicit when-to-use context, no exclusions, and no guidance on choosing it over spss_descriptives or the chart tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It usefully adds the environmental prerequisite ('Requires IBM SPSS Statistics to be installed') and names supported features (multiple link functions, parallel lines test), but it omits key behavioral traits such as whether the tool modifies data, whether it saves predicted values when save_predicted=true, and how results are produced.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no wasted words. The purpose is front-loaded, followed by capability and prerequisite details in a logical order.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 7 parameters, no schema descriptions, and no annotations, so the description must do more. It covers purpose and the SPSS installation requirement, and an output schema exists to explain return values, but it leaves parameter semantics, usage conditions, and side effects largely undocumented.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not compensate. It mentions 'multiple link functions' and 'parallel lines test' generically, but this adds no meaning beyond the enum and boolean already present in the schema. Required parameters (file_path, dependent, predictors) and optional parameters (categorical, save_predicted) receive no semantic explanation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb ('Run') and resource ('ordinal regression (PLUM)') and scopes it to 'ordered categorical outcomes,' which distinguishes it from linear regression. However, it does not explicitly differentiate itself from close siblings like spss_logistic_regression or spss_regression, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'for ordered categorical outcomes' implies when the tool is appropriate, but there is no explicit when-to-use guidance, no when-not-to-use exclusions, and no named alternatives such as spss_logistic_regression. Usage is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It usefully discloses the return format (Markdown table) and the notable constraint that SPSS need not be installed, which is real behavioral context. It does not say what happens on missing files, whether output is truncated when max_rows is hit, or any permission/environment caveats.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the core action and output format, then options, then the environment caveat. Nothing is padded, though the middle sentence is somewhat thin relative to the gaps left elsewhere.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return-value detail is not required. However, for a 4-parameter tool with 0% schema coverage, the description leaves key behaviors (truncation signaling, value-label semantics) undocumented, so it is only minimally sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 4 parameters, so the description must compensate and largely does not. It explains the intent behind 'variables' and row limiting, but says nothing about max_rows' default of 50, its truncation semantics, or the meaning and effect of apply_value_labels (raw codes vs. labeled values).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Read rows of data from an SPSS .sav file') plus the output format ('as a Markdown table'), which is more informative than the title restatement. It implicitly separates itself from metadata/summary siblings, but never names them, so an agent must infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The mention of optional variable filtering and row limiting implies when the tool is useful for targeted inspection, but there is no explicit when-to-use / when-not-to-use guidance and no reference to alternatives like spss_read_metadata or spss_file_summary that also read from a .sav file.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It usefully discloses that it is a read operation and that SPSS does not need to be installed, which is real behavioral context, but it omits failure modes (e.g., missing/invalid .sav file) and any permission or size considerations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the core action and free of redundancy. Each sentence contributes (what it reads, what it returns, and the environment requirement).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple single-parameter read tool with an output schema that documents return values, the description covers the essentials: what is extracted and the no-SPSS-install requirement. Only the lack of sibling disambiguation keeps it from being fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description adds no meaning to file_path beyond its obvious role as the path to the .sav file. With a single self-evident required parameter, the gap is minor, so this lands at mid-range rather than low.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (read) and resource (variable names, types, labels, value labels from an SPSS .sav file) and specifies the return format (Markdown report of file structure). It is clear what the tool does, though it does not explicitly distinguish itself from close siblings like spss_list_variables or spss_file_summary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no exclusions, and no reference to neighboring tools such as spss_list_variables or spss_file_summary that could be confused with inspecting a file's structure. Usage is only implied by the tool name and purpose.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden. It usefully discloses the IBM SPSS Statistics dependency and the statistical outputs (coefficients, R-squared, ANOVA, significance tests), but says nothing about whether files are modified, permissions, pagination, or error behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences with the action front-loaded and no filler. Efficient, though the return-value sentence is somewhat redundant given an output schema exists.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The existence of an output schema means the return-value details are redundant rather than necessary, and the missing coverage of 'method' and 'include_diagnostics' is a real gap for a 5-parameter statistical tool. Adequate but incomplete for its complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 5 parameters, so the description must compensate. It only clarifies 'dependent' and 'predictors' and never mentions 'method' (ENTER default), 'include_diagnostics', or 'file_path' semantics, leaving two parameters entirely undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Run) and resource (SPSS linear regression) and identifies the required inputs (dependent variable, predictors). The word 'linear' implicitly distinguishes it from sibling spss_logistic_regression and spss_ordinal_regression, though it never names them explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to pick this over siblings like spss_logistic_regression, spss_anova, or spss_glm_univariate, nor on method selection or file prerequisites. The only usage note is the environment requirement.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It mentions the prerequisite 'Requires IBM SPSS Statistics to be installed' but omits whether the operation is read-only, what side effects it has, or how output is handled, leaving significant gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, each front-loaded and purposeful: purpose, return content, and prerequisite. There is no wasted language or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be detailed, but the description is still incomplete for a tool with four undocumented parameters and no usage guidance. The prerequisite is helpful but insufficient to cover the missing parameter semantics and behavioral context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 4 parameters and 0% schema description coverage, the description fails to mention any of them. It does not explain file_path, variables, model, or scale_name, leaving the agent to infer their meaning solely from the schema structure.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb (Run) and resource (SPSS RELIABILITY analysis), clarifying it computes Cronbach's alpha. It does not explicitly distinguish itself from siblings like spss_factor or spss_compute_scale_score, so a 4 is appropriate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'for psychometric workflows' hints at context but does not specify when to use this tool versus alternatives such as spss_factor or spss_compute_scale_score. No exclusions or prerequisites beyond the SPSS installation are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden. It usefully discloses the hard requirement that IBM SPSS Statistics be installed, plus the shape of the analysis (within-subject). It does not say whether the tool writes output files, what permissions are needed, or how it behaves on unbalanced designs, and with no annotations that gap is notable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact sentences, front-loaded with the operation and followed by the required inputs and prerequisite. No wasted words, though the parameter sentence is a bare list rather than explanatory.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the SPSS-installed prerequisite is covered. Still missing are guidance on the undocumented file_path/include_pairwise parameters and any routing signal against the many sibling statistical methods, leaving the definition only adequate for a complex analysis tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It maps three of five parameters (within-factor name, levels, variables) but says nothing about file_path or include_pairwise, leaving those semantics entirely undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.