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

Annotations already cover read-only, idempotent, and non-destructive behavior, but the description adds substantial context: daily refresh cadence, 90-day history, newest-first ordering, credit cost, and an unauthenticated preview/rate limit. This is well beyond what the annotations provide.

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 front-loaded and dense with useful details rather than filler. However, the parenthetical list of sources duplicates the source enum and makes an already long sentence heavier.

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?

There is no output schema, and the description gives only a high-level view of returned changed rows, not record fields or pagination behavior. It is sufficient for selecting and invoking the tool, but not fully complete for a six-parameter tool with no output schema.

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 low at 17%, and the description compensates strongly for the most complex parameter, filter, by explaining its source-query-param semantics and giving a concrete example. It maps added/removed/changed to the change enum, but leaves since, page, and per_page to the schema's formats and defaults.

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: rows added, removed, or changed between daily refreshes of named register datasets, newest first, with 90-day history. It clearly distinguishes this from the query_* siblings by telling the agent to poll it instead of re-reading a whole register.

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?

Explicitly says to poll this instead of re-reading a whole register, and points to list_sources for supported_params when using filter. The alternative usage pattern is named, leaving little inference needed.

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