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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior. The description adds meaningful boundary context beyond them: no account or API key needed, records supplied decisions only, and does not run tests, deploy, or establish security/compliance. It stops short of describing how the completeness score is computed or output size limits.

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 sentences, output list front-loaded, then usage routing, then boundary caveats — no filler. It is dense, packing four outputs and two exclusions into one sentence, but every clause earns 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 no output schema, the description carries the return-value burden and does so by enumerating the four returned artifacts. Given 12 required parameters and complex release semantics, the coverage of inputs rests on a fully described schema, so the description is nearly complete, only lacking scoring/format details.

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% across 16 parameters, with enums and constraints documented inline, so the description need not restate them. It adds no format or syntax guidance for the parameters it names, so 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?

States a specific verb and resource: it turns release decisions into four named artifacts (Markdown plan, completeness score, open decisions, PromptBrake gate policy YAML) returned as text. It explicitly differentiates from the sibling build_test_pack, so an agent can select it without opening the schema.

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 an explicit when: 'Use before validating a release to identify missing decisions,' plus a named alternative, 'use build_test_pack for executable response-check definitions.' This routes the agent between the two planning/validation tools without inference.

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