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

Annotations already establish readOnly and closed-world, so the description is free to spend its words on what is actually returned: weekly position, week-over-week change, multi-window click/impression metrics, page-change flags, and 26 weeks of history. The phrase 'from the Project's stored data' usefully discloses that results are persisted rather than freshly fetched.

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?

A single dense sentence with the verb+resource front-loaded and the return payload enumerated afterward in a scannable order. It is long and reads as a run-on, but essentially every clause carries information an agent needs.

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, so the description bears the full burden of describing return values and does so thoroughly, including the history depth and change flags. With annotations covering the safety profile and only two simple parameters, nothing critical is missing.

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 0%, so the description must compensate, and it does so for the key parameter by enumerating the meaningful day windows (7, 28, 90, 180, 365, 480). It leaves projectId undescribed, but that parameter's name and required status make its meaning self-evident.

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?

Opens with a specific verb and resource ('Read the keywords tracked for a Project') and immediately disambiguates the payload: Search Console positions, deltas, clicks/impressions, ranking page, 26-week history. This clearly separates it from sibling list_*_keywords tools, though it never names them explicitly.

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?

Usage context is implied by 'tracked for a Project ... from the Project's stored data', which hints this reads cached project data rather than a live Search Console fetch, but there is no explicit when-to-use/when-to-choose-an-alternative guidance versus get_search_console_overview or list_article_keywords.

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