Tracking coverage & staleness

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

Annotations already establish readOnly/idempotent/non-destructive, so the bar is lower. The description adds genuinely useful behavioral context: it is a current-state snapshot with no date window, and never-checked/overdue counts are scoped only to active queries. It doesn't discuss pagination or response shape, but the safety and scoping profile is well covered.

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 concrete return contents before any framing, which is good. The trailing list of three example question clusters restates the same 'stale/overdue' idea three times and could be trimmed, but overall it stays tight and readable.

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 carries the return-value burden and does so: it lists every count returned plus the overdue sample. Combined with the snapshot/no-date-window note, an agent has everything needed to select and invoke it correctly given its two simple required params.

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% for both parameters. The description doesn't document organizationId or projectId directly, but the phrase 'a project's tracked queries' implies the projectId scope, and both parameter names are self-explanatory. It neither compensates fully nor leaves the agent confused.

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 resource (a project's tracked queries) and enumerates exactly what it returns: total, active, paused, never-checked and overdue counts plus a sample. This level of specificity clearly distinguishes it from sibling tools like get_project_rank_tracking_stats or get_tracked_query_time_series, which cover different dimensions.

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?

Provides explicit triggering questions ('what is stale or not being monitored', 'which queries are overdue, paused, or never checked') and clarifies scope with 'This is a current-state snapshot and takes no date window', implicitly steering the agent away from time-series siblings. It does not, however, name a concrete alternative tool to prefer in adjacent scenarios.

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