What changed recently in AI/dev APIs?

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds real context beyond them: return shape (summary first, then change list with timestamps and source links), a quota/cost model, and an alias (get_changes). That is substantive behavioral disclosure, not repetition.

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-loads what the tool lists, then usage, return shape, example, cost, and alias — a logical order with little waste. Slightly dense and the trailing alias/pricing lines are tacked on, but each 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?

With no output schema, the description carries the return burden and does so (summary plus timestamped, source-linked change list). All four optional parameters are schema-documented, the use cases and cost are stated, and there are no required params an agent could miss.

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 the schema already documents kind, limit, since, and provider including defaults and the enum. The description adds only an example object ({"provider":"anthropic","kind":"model_retirement"}) that reads more like a response item than a filter syntax, so it neither compensates nor extends meaningfully. Baseline 3 applies.

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 and resource (list recent breaking/notable changes across AI and developer APIs) and enumerates the covered categories: outages/recoveries, deprecation-page edits, model retirements, pricing-page edits. That enumeration implicitly distinguishes it from the single-purpose siblings (check_api_status, check_model_deprecation) — this is the aggregate change feed.

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?

Gives concrete usage triggers: answer 'did anything change that could break my integration?' or explain sudden errors. It also flags the cost model (free within daily quota, then $0.01 via x402). It does not, however, name an alternative or state when a narrower sibling like check_api_status is the better pick.

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