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 the resolution precedence (mapping > grid metadata > distribution > default_category) and the return shape (assignment_id plus per-category summary), but says nothing about permissions, whether assignments overwrite existing data, or reversibility for what is clearly a mutation.

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 action and category vocabulary, with the precedence rule second. No filler, though the parenthetical category list is somewhat long.

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 13-parameter mutation tool with no annotations and no output schema, the description covers the core purpose, precedence, and return value, but does not give enough guidance on the many optional knobs (strategy, basis, distribution, include_loads) to be fully self-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 coverage is 69%, so the schema already documents most parameters individually. The description adds relational value by tying mapping, grid metadata, distribution and default_category together via the precedence chain, but leaves several params (seed, strategy, basis, profile_generation, include_loads) 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 ('Assign') and resource ('category ... and profile to every load'), and enumerates the concrete category values an agent can expect. It is clearly distinct from profile-generation siblings like generate_profiles, 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?

Usage is only implied: the tool is for assigning load categories before downstream profile work. There is no explicit when-to-use statement, no exclusions, and no named alternative among the many siblings (generate_profiles, get_grid_loads, etc.).

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 meaningful side effects: it writes CSVs plus a manifest containing settings, assumptions, and checksums, and it returns per-year and ensemble statistics. However, it omits whether the run is idempotent, what auth/permissions are needed, runtime cost for a 23-parameter Monte Carlo call, and whether existing artifacts are overwritten.

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 is front-loaded with the core action and packs outputs into a parenthetical. It wastes no words, though the semicolon-chained clauses demand careful parsing.

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?

Since there is no output schema, the description's note that CSVs, a manifest, and per-year/ensemble statistics are returned is genuinely useful. But for a 23-parameter, no-annotation, write-producing tool, the absence of usage guidance, artifact-overwrite behavior, and precedence among the many scaling/noise options leaves clear 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 65%, so the schema documents most parameters (scaling, reactive, noise_model, n_scenarios, etc.). The description adds only the 'per load and year' framing and says nothing about how the required grid_id, assignment_id, and years combine or how the 20 optional knobs interact, which is the baseline-3 level when the schema does the heavy lifting.

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: 'Generate P/Q time series per load and year,' which is unambiguous. It reasonably distinguishes the tool from siblings like register_profile, get_bdew_curve, assign_load_types, and plot_run, though it never names an alternative to force 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?

There is no when-to-use guidance, no prerequisites, and no comparison to alternatives such as register_profile or load_grid. The agent must infer from the name alone that this is the generation step; nothing in the text routes it.

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 output forms (CSV, plot, statistics) and the normalization unit (W per 1,000 kWh/a), but says nothing about auth, rate limits, or what the returned series represents beyond the unit.

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 wasted words. It is efficient, though its terseness veers toward under-specification rather than true completeness.

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?

Five parameters, no annotations, and no output schema, yet the description documents neither the input parameters nor the structure of the returned CSV/statistics. It is too thin for a tool of this 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 only 40%; profile_id and holiday_subdivision are documented in the schema, while year, resolution_min, and holiday_country are not. The description adds no parameter meaning at all, so it 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+resource: retrieving one BDEW profile for a given year, and notes the output forms (CSV, plot, statistics). The singular 'one ... profile' implicitly distinguishes it from list_bdew_profiles, but 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 description gives no when-to-use guidance, prerequisites, or alternatives. An agent must infer from 'one' that this is the single-profile variant versus list_bdew_profiles, with nothing stated to confirm that routing.

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 hints that the return includes explanations, but says nothing about what defaults are covered, whether any state is required, or the read-only nature beyond the implied 'get'.

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?

It is a single short phrase with no wasted words, but it is under-specified rather than genuinely concise; there is no front-loaded statement of purpose beyond the 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?

For a zero-parameter read tool with no output schema, the description should at least indicate what is returned and in what form. 'Default settings with explanations' is too thin to tell an agent what to expect.

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 are no parameter semantics to document. Per the rubric this is the baseline 4.

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 restates the name ('Default settings with explanations') without a clear verb or resource scope, and gives no way to distinguish it from siblings like list_grids or get_bdew_curve. An agent cannot tell what domain these defaults belong to.

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 indication of when to call this versus the many other getters in the sibling list, nor any prerequisites or conditions. Usage is only inferable from the name.

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 that the operation is paginated and lists the returned columns, which is genuinely useful, but says nothing about permissions, the meaning of the detected 'type' field, or what happens at page boundaries.

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 tight sentence with the verb and returned fields front-loaded; no filler. It is perhaps too terse to be fully useful, but nothing in it 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?

With no output schema, naming the returned columns is the right move and partially compensates. However, the grid_id parameter, paging semantics, and the fact that 'detected type' is inferred rather than declared are left 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 all three parameters, so the description must compensate and largely does not. It lists output columns rather than explaining limit, offset, or grid_id, leaving the paging defaults (limit capped at 40) and the grid identifier semantics 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+resource ('Page through the load table') and enumerates the returned columns, so an agent knows exactly what data comes back. It does not differentiate itself from siblings like load_grid, but the resource is distinctive enough to be 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 statement of when to use this tool versus alternatives such as load_grid or get_grid_curve, and no prerequisites. The only usage hint is the word 'Page', which implicitly signals limit/offset paging but is never spelled out.

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 hints at read-style retrieval modes but never states that the operation is read-only, what happens for an invalid run_id, whether 'verify' performs expensive recomputation, or how output differs per section. Most behavioral traits remain undisclosed.

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?

It is a single short sentence with no padding, which is good, but it is under-specified rather than truly concise — the terseness leaves the reader without a verb or any front-loaded statement of what the call returns by default.

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 no annotations, no output schema, an enum largely undocumented, and a required run_id with no description, the definition is not complete enough for reliable invocation. It should at minimum say that it fetches one run by id, that section defaults to summary, and roughly what each section returns.

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 50% and the enum has ten values, yet the schema documents only summary, methods, and verify. The description partially compensates by naming results, methods text, and checksum verification, but the remaining sections (assumptions, config, assignment, scenarios, resolved, holidays, all) are undocumented in both places, and run_id has no explanation at all.

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 enumerates what get_run can return (results, methods text, a manifest section, checksum verification), which conveys the resource, but it is a noun phrase with no verb and never states that it retrieves a run by id. It also does not distinguish itself from siblings like plot_run or list_runs, so the purpose is inferable but not explicit.

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 mention of prerequisites, and no routing to alternatives such as list_runs (to find a run) or plot_run (to visualize one). An agent must guess that this is the retrieval tool and that run_id must come from 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?

No annotations exist, so the description carries the full behavioral burden. It usefully discloses the scope of content returned (categories, custom profiles, mix syntax), but says nothing about it being a read-only, side-effect-free operation, nor about result size, ordering, or pagination.

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 the verb and resource front-loaded and no filler. The trailing enumeration of content is slightly dense but every clause earns its place by describing the returned data.

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 no output schema and no annotations, the description partially compensates by enumerating what the listing contains. For a zero-parameter read tool this is nearly sufficient, though a note on read-only behavior or result shape would close the remaining gap.

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. Baseline 4 applies; the sentence correctly implies no filtering arguments are required.

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 (BDEW profiles), and enumerates what is covered: profile categories with default profiles, registered custom profiles, and the mix syntax. It is clear what the tool returns, though it does not explicitly distinguish itself from siblings like register_profile or get_bdew_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?

No explicit when-to-use or when-not-to-use guidance is given, and no sibling is named as an alternative. Usage is only implied: this is an obviously safe discovery/browse call for profile data, which an agent can infer but not confirm from the text.

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 discloses the shape of the result (built-in grids plus load-type status), but says nothing about ordering, permissions, or caching. For a simple zero-arg read-only enumeration the gaps are minor, but the disclosure is still 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 sentences, front-loaded with what is listed and immediately followed by the alternative for custom grids. No filler, no restatement 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?

With no output schema and no annotations, the description must cover the return content, and it does specify the two pieces of information returned. It could say more about how the grid list is structured or empty-state behavior, but for a zero-argument enumeration it is nearly 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?

The tool takes no parameters and the schema is an empty object, so there is nothing for the description to disambiguate. Baseline 4 applies; the absence of a parameter-syntax discussion is appropriate rather than a 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 ('List the built-in benchmark grids') plus the returned attribute (whether their load types are known), and it distinguishes itself from load_grid, which handles custom pandapower files. An agent can tell what this returns without opening a 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 second sentence routes the agent to load_grid for custom .json/.xlsx grids, giving a clear alternative and the condition that selects it. It stops short of an explicit when-not statement, but the boundary between built-in and custom grids is unambiguous.

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 ordering (newest first) and session scoping, which is real value, but says nothing about pagination, result limits, whether runs can be missing, or what a run entry contains.

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 sentence that front-loads the action and appends the two useful qualifiers (scope, ordering). Nothing is wasted and nothing extraneous is present.

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 zero-argument list tool with no output schema, the description covers the essential facts an agent needs to decide to call it. It stops just short of describing the shape of a returned run or any result-size limits.

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 clarify; the baseline for a no-parameter tool applies. Schema coverage is 100% trivially.

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 the runs") and adds scope ("of this session"), which distinguishes it from a global run listing. It does not explicitly contrast with the sibling get_run, but list-vs-get is strongly implied by the verb.

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 session scope and newest-first ordering imply when this is useful (browsing recent runs), but there is no explicit guidance on when to prefer it over get_run or plot_run. Usage must be inferred from the verb and from sibling names.

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 bears the full burden. It discloses the returned summary fields, which is useful since there is no output schema, but it does not state whether the operation is read-only, whether it caches or mutates state, or any performance/auth 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?

A single front-loaded sentence with zero filler; the verb and returned content are stated immediately.

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 no output schema, the description helpfully names the summary contents, but it omits usage routing against sibling tools and any behavioral safety profile. For an agent needing to choose correctly among grid-related tools, these gaps matter.

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 100%, so the schema already documents both parameters (grid id/file and include_loads). The description adds no parameter semantics beyond the schema, warranting the baseline of 3.

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 ('Load') and resource ('grid'), and enumerates the returned summary: loads, total power, voltage levels, and load-type status. It does not differentiate itself from siblings like get_grid_loads or list_grids, 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 guidance on when to use this tool versus get_grid_loads, list_grids, or get_default_settings. The description only says what it does, leaving the agent to guess the appropriate 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?

No annotations are provided, so the description carries the full behavioral burden. It does disclose that the return is a PNG image (useful, since there is no output schema), but says nothing about permissions, cost, whether the run must exist, how group_by/loads interact, or pagination/error behavior for an operation with seven parameters.

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 the verb, resource, output format, and the option list — no wasted words. It is terse to the point of under-specification, but structurally 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 seven-parameter plotting tool with no annotations and no output schema, the description covers only the view options. It omits how required run_id/year behave, when group_by=load needs the loads array, and what start_date does beyond the schema's own hints, leaving real gaps 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 43%, so the description partially compensates by mapping view values to human-readable labels (duration -> "load-duration curve", daily_mean -> "daily means"). But it says nothing about run_id, year, group_by, scenario, or how the required year interacts with optional start_date for week/day plots.

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 ("Plot") and resource ("a run") and immediately names the output format (PNG), which distinguishes it from the sibling read/list tools. It also enumerates the available views. However, it does not explicitly contrast itself with any sibling, so it stops short of the 5 bar.

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 prerequisites, and no mention of alternatives among the many sibling tools. The only implied usage is that run_id and year are required, which the schema already enforces. An agent must infer which view to pick and when.

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 important behavior: accepted CSV formats (1 day, 7 days, full year), unit rescaling to 1,000 kWh/a, and optional timestamp column. However, it doesn't mention validation rules, error handling, whether registration is persistent, or any rate limits. Given no annotations, this is partial but not comprehensive.

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 action and format details. No wasted words; the second sentence efficiently links to downstream usage. Could be slightly more structured but is clear and compact.

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 4 parameters, no output schema, and no annotations, the description covers the main input formats and integration point but omits behavioral details like validation, persistence, or error handling. It's adequate but leaves gaps that an agent might need to infer or discover via trial.

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 75%, so the schema documents most parameters. The description adds some semantics: CSV format expectations for csv_path, and implied use of name. However, it doesn't explain step_min (inferred from timestamps if omitted) or the description parameter beyond what the schema provides. Baseline 3 is appropriate when schema does most of the work.

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 ('Register a user-supplied profile') and adds key detail about accepted CSV formats and unit rescaling. Distinguishes it from siblings like load_grid or list_bdew_profiles, which handle built-in/BDew data. However, it doesn't explicitly distinguish 'register' as the setup step versus generate_profiles as the usage step.

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?

Clearly indicates the tool's purpose: adding custom profiles. Mentions how the registered name should be used ('Use its name in category_profiles / load_profiles'), which provides downstream context. But it doesn't state when NOT to use it (e.g., use built-in profiles instead) or compare with sibling alternatives.

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