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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so safety characteristics are covered; the description adds the genuinely new behavioral fact that this must precede other tool usage. It does not state what the response contains (the candidate skill names), though an output schema exists to carry that.

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 mandatory-first instruction front-loaded ahead of the follow-up step. No filler and nothing restates the title or annotations.

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 discovery tool with an output schema and read-only annotations, the description supplies the one thing structured fields cannot: mandatory call ordering and the read_skills handoff. The remaining gap is the relationship to search_docs and whether discovery results persist across calls.

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; nothing about argument semantics needs explaining. The description correctly implies no inputs are required by instructing the agent to just call it first.

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 (discover API guidance and skills) and implicitly distinguishes itself from read_skills by describing discovery vs. loading. It does not clearly distinguish itself from the sibling search_docs, which also appears to be a lookup-style tool, so an agent must infer which discovery path applies.

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 prescribes ordering ('Call this FIRST before using other etabs-mcp tools') and names the follow-up step with read_skills, which is exactly the routing an agent needs. It omits any exclusion, such as whether it is safe to skip once skills were already discovered earlier in a session, so it stops short of 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?

Adds meaningful sandbox behavior beyond the annotations: blocked imports, dir(), getattr(), and dunder access, plus how model, input_data, json, and math are provided. It also explains the return mechanism, though it does not cover error handling or timeout 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?

The description is three tight sentences, front-loads the core action, and includes only operationally useful constraints. No sentence 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?

Given the annotations, full schema coverage, and output schema, the description supplies the key sandbox constraints and execution model an agent needs. It is complete enough for a destructive code-execution tool whose schema already documents instance, overwrite, and output paths.

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 100%, so parameter documentation is already strong. The description still adds useful semantics for code execution by explaining the pre-connected model variable, optional input_data injection, and result return path.

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: execute Python code in a sandbox against the ETABS COM API. It also names prerequisites (discover_api and read_skills first), which helps an agent distinguish this from simpler API-discovery 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?

Gives a clear prerequisite to call discover_api and read_skills first before using this tool. It does not explicitly say when to choose this over siblings like get_model_geometry, but the usage context is clear.

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?

Annotations already cover readOnly, idempotent and closed-world, so the description earns credit for going further: it discloses the non-destructive side effects (locks, analysis results and ETABS windows preserved) and the access mechanism (COM API only, no desktop control). That is exactly the context an agent needs to trust the call in a headless workflow, though the read-in-metres vs preserve-model-units phrasing is slightly ambiguous.

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, front-loaded with the payload types and followed by the two behavioral guarantees. No filler and nothing 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?

An output schema exists so return values need no explanation, and the safety profile is well covered. However, for a tool that can silently cap results at 20,000 objects, the absence of any note on `max_objects` or truncation leaves a real operational 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?

Schema description coverage is 0% and the description mentions neither `instance` nor `max_objects`. The 20000 default on max_objects strongly suggests a truncation or pagination cap that an agent must understand before relying on results, and nothing here explains it.

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 enumerates the exact resource types (point, frame, area, opening, story geometry) plus the unit (metres). This clearly separates it from render_model_view, though the description never names that 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?

Usage is only implied: an agent can infer this is the data-extraction path rather than the visual-rendering one, but no alternative is named and no when-not condition is given. The 'never reads or controls the desktop' line is a constraint, not a selection guideline.

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?

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description adds value by naming the returned fields (connection state, version, model path, lock status). It says nothing about failure behavior when no instance is connected, and the idempotentHint=false flag goes unexplained.

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 paragraphs: purpose first, then parameter behavior, then return contents. No filler and nothing 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?

For a one-optional-parameter read tool with annotations and an output schema, the description covers purpose, parameter semantics, and a summary of returns. An agent has everything needed to invoke 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 coverage is 0%, so the description must carry the parameter, and it does: it identifies ``instance`` as an alias from list_instances, states its targeting purpose, and specifies the omit case for the null default. Only the accepted alias format is left unstated.

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 connection to an ETABS instance') and lists the concrete outputs, so the agent knows exactly what it gets. It implicitly separates itself from list_instances by treating that tool as the source of the alias, but never 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?

Gives a clear conditional rule: supply ``instance`` to target a specific instance, omit it when only one is running. That resolves the main ambiguity of a single optional parameter, though it offers no guidance on when to call this versus siblings like prepare_session or list_instances.

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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds genuinely new behavior: alias stability across the server session and a conditional warning field when a version falls below 21.0.0. It does not discuss ordering or performance, but for a zero-arg read those are non-issues.

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 paragraphs, front-loaded with purpose, then usage, then edge case — nothing wasted. The enumeration of return fields partially duplicates the output schema, which is the only minor redundancy.

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 description need not detail the return shape, yet it still flags the one non-obvious behavior (version warning) and the key operational fact (stable alias). Combined with annotations and zero params, an agent has everything needed to call 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?

The tool takes no parameters, so there is nothing to disambiguate; the baseline of 4 applies. The description instead spends its words on the returned alias and version semantics, which is the right trade-off.

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?

Opens with a specific verb and resource ("List all running ETABS instances") and immediately enumerates what each entry contains, so an agent knows exactly what it gets back. It is unambiguous against siblings like get_status or get_model_geometry, which do not enumerate running processes.

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 states the call condition — "Call this before execute_code when multiple ETABS instances may be running" — and names the sibling that depends on it. There is no explicit when-not clause, but the conditional phrasing strongly implies the single-instance case does not require 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?

Annotations only declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false. The description adds real substance beyond that: existing files and unsaved geometry are never reset or overwritten, a new model is saved under a unique file, new_model=True spawns a separate ETABS process, the tool performs no clicking/typing/window creation, and authentication is completed manually by the user.

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 core action, then the when-to-use condition, then the mode branching — a sensible order. A few clauses restate the title's 'without desktop automation' point ('does not click, type, arrange other apps, or create view windows'), which is mild redundancy but still earns some place as a scope boundary.

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 described, and safety behavior is well covered. However, for a 9-parameter tool with zero schema descriptions, the description leaves the geometric parameters and the meaning of 'instance' (a sibling list_instances exists) unaddressed, so an agent must guess how to target an existing process.

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. It explains the two decision-critical parameters well (new_model and omitting instance) and supplies the unit ('grid in metres') for the grid parameters, but stories, spacing_x/spacing_y, grid_lines_x/grid_lines_y, story_height and first_story_height are never individually explained, nor is it stated whether the grid parameters are ignored when new_model=False on a loaded model.

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: opens ETABS if needed and prepares a usable session, with the distinguishing constraint 'without computer-use'. That constraint separates it cleanly from siblings like execute_code and render_model_view, so an agent can pick it without opening any 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?

Explicit when-to-use: 'Call this before creating geometry on the Start Page or when ETABS is closed.' It then branches the usage by mode — new_model=True (omit instance) for a new building, new_model=False for a loaded model — which is exactly the decision an agent must make.

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?

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds useful context that the returned content is domain guidance, but says nothing about behavior for unknown skill names or the size/shape of returned content (an output schema exists, so that is partially excused).

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 action and followed by the prerequisite. Minor redundancy in repeating the discover_api pointer that the parameter schema also carries.

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 one required parameter, full schema coverage, annotations, and an output schema, the description covers the essential call path plus the prerequisite lookup. Only error behavior for invalid skill names is left unstated, which is a minor 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?

Schema description coverage is 100% and the single parameter is documented as a list of skill names with a pointer to discover_api. The description adds no format, casing, or multiplicity guidance beyond the schema, so baseline 3 applies.

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 one or more skills by name") and clarifies what a skill contains (domain-specific guidance for analysis, geometry, loads). It is distinguishable from siblings like search_docs, though it never explicitly contrasts with them.

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 an explicit prerequisite: "Use ``discover_api`` first to list available skills," which routes the agent to the correct sibling before calling this one. It stops short of stating exclusions or what to do if a named skill is unavailable.

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?

Annotations only declare the safety flags (readOnlyHint=false, idempotentHint=false, destructiveHint=false); the description adds genuinely new context: output format is a PNG (drawing, not screenshot), the file is saved to Documents/ETABS-MCP/exports, the filename is unique per call (which explains the non-idempotent hint), and no UI interaction occurs. It stops short of describing failure behavior (e.g., plan without a story) or whether the response returns the path.

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 output format and the no-screen-access guarantee are front-loaded, followed by the view/story rule and the file-save detail. The closing sentence listing clicks, keys, focus, menus, and native window changes is slightly redundant with 'no screen access' but reinforces a key constraint, so it roughly 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?

For a 5-parameter tool with no output schema, the description covers the core behavior and side effect (file written to a known folder) well. It leaves gaps on three undocumented parameters, on what the call returns (path? inline image?), and on error conditions, which are material 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%, so the description carries the full burden, yet it only explains 'view' (3d/plan/elevation) and 'story'. The 'width', 'height', and 'instance' parameters — including the instance selector for multi-instance setups — are given no meaning in either schema or 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+resource ("Generate and return a PNG from ETABS API geometry") and explicitly distinguishes the output from screenshots. An agent can tell this apart from get_model_geometry (raw geometry data) and from any window-based rendering, especially given the title's 'without desktop access' framing.

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 gives conditional parameter guidance ("For a plan specify an exact story such as Story3") and enumerates the valid view kinds, which is useful. However, it never states when to choose this tool over siblings like get_model_geometry or execute_code, nor any prerequisites or exclusions. Usage is implied, not routed.

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?

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint=false, so the safety profile is carried for free. The description adds genuine value on top by describing what a call produces (matching API methods with their Python calling convention), which tells the agent the result is directly usable code-shaped output.

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 purpose and followed by the return content and the workflow cue. Efficiently structured 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?

For a two-parameter read-only search with full schema coverage and an output schema, the description covers purpose, output shape, and workflow placement — enough to invoke correctly. The one missing element is sibling disambiguation against discover_api.

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% — the query parameter already shows natural-language examples and top_k already documents its default and max. The description adds no syntax, length, or specificity guidance for the query beyond what the schema says, so baseline 3 applies.

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 uses the specific verb and resource ("Search ETABS API documentation") and states the query modality (natural language). It stops short of distinguishing itself from the overlapping sibling discover_api, which an agent could reasonably read as doing the same job.

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?

Clear workflow guidance: use this to discover method names, parameters, and return format *before* using execute_code, which names a concrete alternative. The gap is the same as above — the closely related sibling discover_api is never mentioned, so the agent gets no rule for choosing between two discovery tools.

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