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

Annotations already declare read-only/idempotent/non-destructive, so the bar is low, yet the description adds substantial context: it is FREE (database-only, no provider call, no credits spent) and discloses a real detection limitation — a rank check records only the single best-ranking URL per keyword per run, so a second own page in the SERP cannot be seen. That is exactly the kind of operational caveat annotations cannot convey.

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 the definition before the disambiguation and the caveat, and every sentence carries information (free/no-credits, sibling contrast, detection limitation). It is dense but not padded; only the SERP-caveat sentence is long relative to its weight.

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 still covers what is returned, its data source, its cost profile, and its accuracy limits, plus the alternative tool — everything needed to call and interpret it correctly.

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% and both parameters (projectId, configId) are fully documented with acquisition paths in the schema, so the baseline of 3 applies. The description adds no parameter-level syntax or constraints beyond what the schema already provides.

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 precise verb+resource+condition: 'Tracked keywords whose latest ranking URL is not the target URL you declared for them.' It explicitly names the sibling it is NOT (get_cannibalisation_report) and points to the setup tool (set_rank_keyword_target_url), so an agent can distinguish it without opening any 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?

Gives explicit when-not guidance by contrasting this detector with the Search Console-based get_cannibalisation_report, and clarifies the underlying data source. The setup prerequisite (declared target URL via set_rank_keyword_target_url) is also named.

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