model_retirements

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

With no annotations, the description carries the full behavioral burden and does well: it discloses the data source (LiteLLM feed), refresh cadence (weekly), default look-ahead window, and the 90-day retroactive inclusion. It does not mention rate limits, auth, or result pagination, 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?

Front-loaded with what the tool returns, then usage examples, then sibling routing – a sensible order with no filler sentences. The opening sentence is a long run-on clause chain that costs a little readability, but every sentence carries information.

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?

No output schema, so the description correctly explains what each result contains (date, days left, newest non-retiring same-family model, list price change). Combined with source and freshness disclosure, an agent has enough to call and interpret it; only pagination/ordering behavior and rate limits remain unstated.

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%, so all four parameters are already documented, giving a baseline of 3. The description adds only framing around the window concept and the same-family/same-provider replacement logic; it adds no per-parameter syntax or interaction rules beyond the 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?

States a specific verb+resource: models with retirement dates in a window across named providers (Bedrock, Azure OpenAI/AI Foundry, Vertex, OpenAI, Anthropic), plus those retired in the last 90 days. It also spells out the returned fields (date, days left, same-family replacement, price change) and names the price-focused sibling llm_price_changes implicitly by contrast. An agent can distinguish it from all siblings without opening a 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?

Explicit 'Use for:' phrasing with three concrete user questions covering list, single-model check, and replacement lookup. It also routes away from itself by noting analyze_ai_spend and review_agentcore already flag retiring models automatically, which tells the agent when this tool is redundant.

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