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

Annotations already establish readOnlyHint=true/destructiveHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: it discloses the default grouping (per-agent), the alternate grouping (PR), and the kinds of values returned (parity verdicts, model IDs, score definition, estimated cost delta). It omits pagination/cursor behavior and the superadmin-only nature of customerId, keeping it from a 5.

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 tightly packed sentences: purpose and payload first, mode/default behavior second, intent-matching example questions third. No redundancy and nothing buried — every sentence contributes to selection or invocation.

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 an 8-param, no-output-schema read tool, the description does the heavy lifting of describing the returned content (verdicts, model IDs, score definition, cost delta), which compensates for the missing output schema. It leaves cursor/pagination and status-filter semantics entirely to the schema, so it is strong but not fully complete.

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%, so the schema already documents all eight parameters (including the view enum and its default). The description reinforces view semantics and default grouping but adds no new syntax, format, or constraint detail beyond what the schema states; baseline 3 applies.

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?

Specific verb+resource ('see whether deployed fixes or model swaps worked in production') with an explicit enumeration of what the response contains (parity verdicts, model IDs, score definition, cost delta). It also distinguishes its two modes — per-agent by default vs PR-grouped with view='pr' — so an agent can tell it apart from neighbors like get_pr_context or get_score_timeline.

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 clear usage context via the default grouping rule and the 'view=pr' alternative, plus three example questions ('did my fixes work?', 'what PR changed this?', 'show me PR impact') that map intent to invocation. It does not, however, name a competing sibling tool or state when NOT to use it, so it stops short of explicit alternative routing.

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