generate_eval_suite

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

With no annotations provided, the description must carry the full burden of behavioral disclosure. It states that the tool binds a corpus to a manifest, implying a creation/persistence action, but does not specify whether this is a read-only operation, whether it overwrites existing suites, or what side effects occur. The term 'deterministic' hints at properties of the output but not at tool behavior. This is a significant gap for a tool that likely has 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?

The description is a single, concise sentence that front-loads the core action without unnecessary fluff. It is well-structured for quick parsing, though it could have been slightly more explicit about the parameters in the same length.

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 has 3 parameters, nested objects, and an output schema, this description is far too brief. It does not explain what a valid 'case' looks like, what 'deterministic' means in practice, how the migration_plan should be structured, or what the output (bind) represents. The presence of an output schema does not reduce the need to explain inputs and behavior. An agent would likely need to inspect the schema and make many assumptions to use this 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% (no property descriptions), so the description must compensate. It mentions 'migration manifest' (likely migration_plan) and 'evaluation corpus' (likely cases), but does not map these terms directly to the schema parameters or explain their structure. It also omits the 'name' parameter entirely. The agent cannot infer parameter formats, relationships, or requirements from this 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?

The description uses a specific verb ('Bind') and names both the input (migration manifest) and the product (deterministic evaluation corpus). It distinguishes itself from siblings like run_migration_eval (which would execute the suite) and generate_migration_plan (which creates the plan) by indicating it creates a binding between the two. However, 'Bind' is less idiomatic than 'generate' or 'create', and the phrase 'evaluation corpus' is slightly vague without further context.

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 indication of when to use this tool versus alternatives. It does not mention, for example, that this tool is a precursor to run_migration_eval, or that it should be used after generate_migration_plan. An agent would have to infer usage from the tool name and siblings, which is insufficient.

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