models

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

No annotations provided, so the description carries the burden. It thoroughly discloses what the contract includes (types, domains, constraints, sentinel meanings, constants with sources) and what include_spec adds (full spec with formulas, assumptions, exclusions, known issues). This is solid behavioral disclosure for a read-only retrieval 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 purpose, then a useful conditional detail. Each sentence earns its place; no redundancy or fluff.

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 simplicity (2 params, no output schema), the description is complete. It explains what the tool returns in detail and what the optional flag does. The sibling tools are not referenced, but that's not necessary for invoking this 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 description coverage is 100%, so baseline 3 applies. The description adds minimal extra semantic value beyond the schema: it clarifies the contents of the contract and the markdown, but doesn't introduce new meaning for params. Schema already defines model and include_spec adequately.

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 a specific verb ('get') and resource ('model's machine-readable contract'), then enumerates specific contents. It clearly distinguishes from siblings: list_models lists models, run_model executes, this retrieves contract 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?

No guidance on when to use this tool vs alternatives. The conditional include_spec parameter instruction is the only usage hint, but there's no mention of scenarios like 'before running a model' or 'when you need input requirements'. Lacks explicit when/why.

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 present; description discloses that the tool is a listing operation (read-only) and adds quality context (dual-implementation tested). Does not explicitly state side effects, but not needed for a list 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 sentences: purpose, return value, and next-step guidance. No filler 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?

Includes what it returns (model names and spec versions), the verification criterion, and the proper next step (get_model_contract). Sufficient for a zero-parameter list 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?

No parameters in the schema; baseline of 4 applies. Description adds no parameter details because none exist.

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?

Clearly states it lists verified financial calculation models, with the qualifier of dual-implementation testing. Distinguishes from sibling tools (get_model_contract, run_model) by being the enumeration 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?

Guides the user to call get_model_contract before running a model, establishing a workflow. Doesn't explicitly contrast with alternatives, but the sequential instruction makes usage 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states that out-of-domain requests are rejected and never clamped, details the response contents (inputs, spec version, assumptions, sentinels, sourced constants), and confirms outputs are exact. This is thorough for a calculation tool, though it omits auth or rate limits.

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 sentences long, each serving a distinct purpose: action, contract enforcement, and response/usage. It is front-loaded with the verb and contains no fluff. The inclusion of the share URL is pragmatic and does not detract from clarity.

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 nested object and lack of output schema, the description compensates well by describing the response structure. It references sibling tools for context and provides a real-world sharing URL. It does not specify error formats or authentication requirements, but these are less critical for a scenario model runner.

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 schema already defines 'model' and 'inputs' with basic descriptions, giving 100% coverage. The description adds meaningful operational semantics by explaining that inputs must adhere to contract domains and that violations are rejected rather than clamped, augmenting the bare schema definitions.

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 explicitly states the action ('Run') and the resource ('a verified calculation model'), making its purpose immediately clear. It distinguishes itself from siblings list_models and get_model_contract by focusing on the execution step rather than listing or contracting.

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 specifies a clear prerequisite: inputs must satisfy the contract from get_model_contract, implying users should retrieve that contract first. It also provides a post-action share instruction. However, it does not explicitly mention when not to use this tool or name alternative tools for other situations.

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