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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the trailing 'Read-only' sentence simply repeats structured data and earns no credit. What it does add is behavioral meaning for the returned numbers, defining how cycle time and throughput are computed, which lets an agent interpret the output. It says nothing about empty-data behavior, default window when days is omitted, or aggregation caveats.

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 sentences, front-loaded with the metric inventory and followed by the intended use case, so the most decision-relevant information comes first. The closing 'Read-only' is redundant against the annotations and is the one phrase that does not earn its place.

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 2 optional parameters, no nested objects, and no output schema, the main gap an agent faces is not knowing what comes back, and the description fills that by enumerating and defining the four metric families. It is nearly complete for this complexity level, with only return shape and pagination/period semantics left implicit.

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 100%: both parameters, days and teamId, are documented in the schema with the 30-day default. The description adds no syntax, format, or filtering nuance beyond that, so the baseline of 3 is appropriate when the schema carries the parameter burden.

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 names a specific verb and resource and goes further by defining the four metrics returned: cycle time, throughput, review health, and PR size trends, each with an inline definition (e.g., cycle time = first commit to merge). That is far more specific than a bare 'get summary'. It stops short of distinguishing itself from siblings like get_at_risk_prs or get_open_prs, which is why it falls short of a 5.

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 a clear usage context: assess code review efficiency and identify bottlenecks in the delivery pipeline, which tells an agent this is an aggregate analytics tool, not a per-PR listing tool. It does not explicitly exclude alternatives or say when to prefer get_at_risk_prs or get_open_prs instead, so routing is only partly supported.

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