sumo_qa_format_qa_scorecard

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description adds real behavioral content beyond them: the four verdicts, the refusal rule for uncovered blockers and stale evidence, and the hard dependency that a bundle naming a head_sha cannot support 'ready' without local_head_sha. It stops short of describing what the returned scorecard contains (e.g. the reasons list / truncation).

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?

The verdict list and the refusal invariant are front-loaded, and every sentence (including the parenthetical ledger field enumeration) earns its place by disambiguating inputs. It reads as a dense run-on with multiple nested parentheses, which slightly hurts scanability, but there is no filler.

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 a 7-parameter, no-output-schema tool this description is close to complete: it defines the decision space, the refusal conditions, and the input contracts that matter for correctness. What is missing is the shape of the result (reasons, and how max_reasons bounds them), which matters more here because no output schema exists to document it.

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?

With 0% schema description coverage, the description must carry the parameters, and it largely does: it enumerates the ledger_rows fields and their status/residual value spaces, points to sumo_qa_format_context_bundle for the context_bundle shape, explains that absent coverage/mutation means 'not measured', and states the local_head_sha constraint. The notable gap is max_reasons, which is undocumented in both schema and description.

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 opens with a specific verb and resource ('Compute QA readiness... from existing evidence') and enumerates the exact verdict space (ready / ready_with_accepted_residuals / blocked / insufficient_evidence), so an agent knows precisely what this tool produces. It does not, however, name or contrast itself with close siblings such as sumo_qa_generate_qa_report or sumo_qa_reviewing_before_merge, which an agent choosing among merge-gate tools would want.

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?

'from existing evidence' and the list of optional inputs imply the precondition (you supply ledger rows / a context bundle) and the invariant 'an uncovered blocker or stale evidence refuses ready' hints at when a 'ready' answer is trustworthy. There is no explicit statement of when to prefer this over sibling reporting/review tools, so the usage guidance is inferable rather than stated.

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