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

The tool's annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=falseais. The description adds meaningful behavioral context beyond annotations: it confirms no execution occurs, details what the dry-run returns for each kind (resolved_plan, plan_hash, invocation_hash, etc.), and notes the login requirement with offline operation afterward. This is exactly the kind of context that aids correct invocation.

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 compact yet information-dense. The first sentence states the core purpose immediately. The second sentence adds specific return artifacts for both kinds, a usage directive, and a prerequisite, with no filler. The structure is front-loaded and 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?

Given the tool's two distinct modes and complex schema, the description covers both modes completely, specifies what results to expect, explains when to use it, and notes environmental requirements. It does not need to explain return values because there is no output schema, and it correctly avoids redundancy with the input schema. No missing information blocks 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 100%, so the schema already documents parameters like metric, source, and seed. The description adds semantic value by explaining the role of the 'kind' discriminator and what each kind validates or returns, which is not explicit in the schema. However, it does not go into per-field detail for the spec objects, though the schema covers that thoroughly, so a 4 is appropriate.

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 'Dry-run a queryData request without executing it,' which clearly states the verb, resource, and key constraint. It then explains the two kind variants (query vs computation) and explicitly positions it against queryData, so an agent can distinguish it from the execution tool without needing to compare schemas.

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 direct usage guidance: 'Use this to debug clarifications and rejections before running queryData.' This tells the agent when to select this tool over queryDataced and also implies the alternative. It further explains for computation kind what to check (capability existence, signature, seed requirement), covering both branches of behavior.

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 readOnly, idempotent, and non-destructive hints, but the description adds substantial behavioral context: in-memory storage, 15-minute TTL, oldest-first eviction under memory pressure, a structured result_not_found error, the 10 MB output-size cap, and authentication requirements. This is context the annotations cannot convey.

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 purpose and usage, then moves through storage behavior, error handling, and auth. It is longer than average, but every sentence provides distinct information needed to call the tool reliably; no filler 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?

Even though there is no output schema, the description covers the result semantics (full vs. truncated), error behavior, storage lifecycle, size cap, and how to regenerate results. The single parameter is fully explained, leaving no critical gap in the agent's ability to use the tool 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 100% and the schema already documents result_id as coming from a queryData ok result. The description goes beyond this by explaining the lifecycle of that id (expiry, eviction, regeneration) and what happens if the id is invalid. This adds actionable meaning beyond the bare 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 opens with a specific verb and resource ('Fetch the full stored result of an earlier queryData call by its result_id') and contrasts it with the truncated preview from queryData. It explicitly names the sibling tool it depends on and the condition under which it is relevant, so an agent can identify it 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 states exactly when to use this tool ('Use it when queryData returned truncated: true') and provides the alternative action when the result_id is unavailable: re-run the original queryData request. It also clarifies that the tool takes no other parameters, which thins the decision space for an agent.

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 readOnly, idempotent, non-destructive, and closed-world behavior. The description adds meaningful context beyond those: auth requirements (free community login or SQAI_API_KEY), the deterministic nature of the computation catalog, and the offline-after-login behavior. This is useful but does not describe edge cases or exact output formatting.

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 dense but organized: it front-loads the purpose, separates the three modes with clear markers, and ends with the necessary login note. Every sentence carries load-bearing information, with no filler or 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?

For a no-required-params discovery tool with no output schema, the description tells the agent what to expect from each mode, states prerequisites (login/API key), and explains why it should be called before queryData. No important aspect of correct invocation is left unspecified.

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 baseline is 3 and the schema already explains both optional parameters. The description adds the default no-argument mode and calls the capability catalog deterministic, but essentially restates the schema's parameter descriptions rather than adding substantial new semantics.

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 the role ('Discover what SQAI can touch') and then specifies three concrete modes: listing connected data sources with exact field names/types/allowed operations, searching the capability catalog, and listing module functions with exact signatures. It also differentiates from the sibling queryData by instructing the agent to call it before queryData so specs use exact names.

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 explicit guidance for the main workflow: 'call this before queryData so specs use exact names,' and it explains when to use the capabilitySearch and module variants. It does not explicitly state when to prefer queryData or explainQuery, so it stops short of full when/when-not coverage.

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 declare readOnlyHint, idempotentHint, and destructiveHint=false, and the description aligns and reinforces these with 'deterministic, read-only'. It adds beyond annotations by disclosing truncation behavior ('Large results are truncated for context; the full result stays retrievable'), the authentication requirement ('free community login'), the seed requirement for simulations, and the offline capability. No contradictions; the description enhances the safety and behavior profile.

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 concise for the tool's complexity—about 90 words—and front-loads the core purpose and kind routing before diving into details. Each sentence earns its place: kind distinctions, bindings advice, seed requirement, truncation handling, and auth. The only minor inefficiency is that the truncation detail could be seen as part of output behavior, but it is necessary context. It is dense but well-organized.

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 description is complete despite the tool's high complexity (two distinct schemas, QA vs computation). It explains both usage modes, the necessity of listSources for field discovery, the truncation-and-getResult recovery path, auth requirements, and the seed requirement for simulations. All critical invocation aspects are covered, and the absence of an output schema is mitigated by mentioning getResult and result_id. Nothing an agent needs to call it correctly 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?

Schema coverage is 100% and includes descriptions for metric, source, group_by, module, function, bindings, seed, and filter fields. The description adds semantic context beyond the schema: it explains the conceptual distinction between query and computation kinds, advises using bindings instead of pasting data, and mentions the seed requirement explicitly. It doesn't enumerate every parameter name but adds strategic guidance on how to use them, which is valuable above the schema's individual descriptions.

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 ('Execute'), a specific resource ('one deterministic, read-only SQAI request'), and distinguishes two usage kinds (query vs computation) with concrete examples. It explicitly names sibling tool listSources for discovery, preventing confusion with getResult and explainQuery. The purpose is unambiguous and actionable.

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 explicit when-to-use guidance for each kind ('Use kind 'query' for tabular questions (aggregations, grouping, filtering)', 'Use kind 'computation' for math (statistics, financial, vector/matrix, simulation)'), states the alternative for large data (bindings vs pasting), and mentions the getResult tool for retrieving truncated results. It also covers prerequisites (listSources first, login requirements) and identifies when not to use it (never paste large data).

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