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

Beyond the readOnlyHint, it discloses that calls are free and never consume lookups, and it honestly scopes the data as computed movements rather than user-configured alerts. It also reveals that events carry Google-update-date annotations, adding behavioral detail annotations do not cover.

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?

Three dense sentences carry the definition, exclusions, parameter source, and cost behavior with no filler. The most important identifying information is front-loaded in the first sentence.

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?

For a two-parameter read-only tool with an output schema, the description covers all necessary invocation context: what it returns, how to identify the project, the time window, the cost implications, and the borderline between computed events and alert rules.

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?

With 0% schema description coverage, the description compensates fully: days is explained as the trailing N-day window with the 7–90 range restated, and project_id is given real meaning as a 'ranking id from list_projects' rather than just a positive integer.

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?

The description opens with a precise definition: threshold-crossing ranking events for a single project over a 7–90 day window, including exact event types (entering/leaving top 3/10/100, big gains/drops). It also distinguishes this tool from saved-alert rules, which prevents confusion with the 'alerts' label.

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?

It gives clear usage context: one project, last N days, project_id sourced from list_projects. It explicitly says this is not a saved-alerts feature, offering a when-not, though it does not name a concrete sibling alternative for saved alerts or current rankings.

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