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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds two real behavioral facts beyond that: the percentile metrics are nullable (no data yields nulls) and results are bucketed by UTC day. It says nothing about pagination, result size, or what an empty window returns.

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?

Two short sentences, front-loaded with the returned metrics and no throat-clearing. 'P50 is median' is nearly filler for a technical agent, but it is defensible disambiguation and costs little.

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?

An output schema exists, so explaining return values is not required — which makes the description's focus odd, since it describes only outputs and omits how to scope the query (window/filters) or when to select this tool. For a 2-parameter analytics tool with 0% parameter coverage, this leaves the agent without the information needed to call it well.

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 the two top-level parameters, and the description never mentions 'window' or 'filters' at all. The AnalyticsWindow $def clearly documents its half-open UTC semantics, but the genuinely undocumented AnalyticsFilters (repo_names, workflow_ids, head_branches) is left to the agent to guess, so the description does not compensate for the coverage gap.

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 verb is 'Read' and the resource is implied ('run stats' only via the tool name), but the sentence spends its budget enumerating output metrics rather than stating what the tool does. It gives no basis for distinguishing it from a sibling like 9apes_get_job_stats or 9apes_compare_windows.

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?

There is no when-to-use guidance, no stated precondition, and no named alternative among the eight siblings (get_job_stats, compare_windows, rank_jobs, etc.). The agent must infer the choice purely from the name.

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