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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does convey that the tool filters by announced retirement date and sorts results, but it does not explain how the 'horizon' is determined or whether the output includes any additional fields or pagination. For a read-only listing tool, this is moderately transparent but not rich.

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, front-loaded sentence that conveys the core action, subject, and sorting order without wasted words. It is appropriately sized for the tool's simplicity.

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 (one optional parameter, no output schema), the description is mostly complete but has a key gap: it fails to explain that the horizon is the within_days parameter. Without this connection, an agent might not know how to control the horizon. The description also assumes familiarity with 'models' in the domain context.

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 has one parameter, within_days, with 0% description coverage. The description mentions 'inside a horizon' but never explicitly connects this to the within_days parameter, leaving the agent to infer that the horizon is the parameter's value. It does not specify that within_days is measured in days or that it defaults to 90, so the parameter's meaning is under-explained.

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 clearly states the tool's function: listing models with an announced retirement date within a specified horizon, sorted by soonest date first. The verb 'List' identifies it as a read-only retrieval operation, and the resource ('models with an announced retirement date') and ordering ('soonest first') distinguish it from siblings like 'recent_changes'.

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 implies the context of use: to find models retiring within a time horizon. It does not explicitly mention alternatives or exclusions, but the 'soonest first' ordering and 'inside a horizon' phrasing suggest this is for planning ahead. The sibling names (check_model, check_models, recent_changes) imply different purposes, so the description gives enough context without explicitly naming alternatives.

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