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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's job is return behavior — and it delivers: per-engine rank, previous rank, change, ranking URL, up/down/gained/lost keyword buckets, competitors tracked, and the crucial "null = not in the top 50" semantics. It does not cover edge cases like an invalid run_id or a report with only one run, which keeps it below 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?

A single front-loaded sentence with the core operation first, then the return shape, then the `runs` note — the semicolon-separated clauses keep it scannable despite its density. Every clause carries information, though the sentence is long enough that a reader must parse carefully.

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 must carry the return-value burden, and it does so in detail, including comparison semantics against the prior run. The remaining gap is behavioral edge cases (single-run reports, invalid run_id), which are non-trivial for a comparison-based report but do not block correct invocation.

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 the baseline is 3; the description earns an extra point by restating the run_id default ("the latest unless run_id is given") and by explaining that `runs` enumerates every available run, which is otherwise only implied by the schema's cross-reference. No format or constraint details are added beyond that.

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+resource ("Read a Rank Tracker report") and immediately scopes the content: per-keyword positions on Google, Maps and the local pack, with changes. That distinguishes it cleanly from list_rank_tracker_reports and update_rank_tracker_keywords in the sibling set.

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 is implied rather than stated: "Returns one run of the report (the latest unless run_id is given)" tells the agent the default behavior, and the routing to list_rank_tracker_reports lives in the schema, not the description. There is no explicit when-to-use vs. when-not guidance or mention of prerequisites such as the report needing at least two runs to compare.

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