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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's real contribution is the scoping semantics: a record scoped to some code is returned with that scope spelled out and never as an unconditional hit. That is non-obvious behavioral detail an agent could not get from annotations. It doesn't discuss truncation or partial-failure behavior when some identifiers miss, which keeps it from a 5.

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 sentences, front-loaded with the verb and the identifier categories, then the answer shape, then the scoping caveat. The parenthetical about repos depending on an SDK major version is long but it is the clearest illustration of the scoping rule, so it earns its space.

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 needn't explain return values, and annotations cover the safety profile, so what remains — what inputs are valid, what comes back per identifier, and how scoped hits differ — is all addressed. A missed-identifier or empty-result case is the only notable omission.

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 single parameter is well constrained, so the baseline would be 3; the description adds value by enumerating what counts as an identifier (model ids, endpoints, MCP tool names, SDK methods, field names) and restating the 100-item cap. That said, the description provides no batching or normalization guidance for inputs beyond the example list.

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 gives a specific verb ('Look up') plus a concrete resource set — model ids, API endpoints, MCP tool names, SDK methods, field names — and the phrase 'many identifiers at once' distinguishes it from the single-lookup sibling check_model. It stops short of naming the sibling explicitly, so the differentiation is implied rather than stated.

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?

'before shipping code' gives a genuine usage context, and 'many at once' hints at when to prefer this over check_model. There is no explicit when-not guidance and no sibling named as an alternative, so the routing decision is left partly to inference.

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