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

Annotations declare a non-readonly, non-destructive, non-idempotent closed-world write, and the description adds genuinely new context: an auth requirement (FIXLORE_KEY), a data-handling constraint (never include secrets), and the quality-gate outcome model (BLOCK/WARNING/PASS). These additions go beyond what the annotations convey, though nothing is said about whether a blocked submission is persisted or how non-idempotency manifests on retry.

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 tight sentences with zero filler, and the core action plus the field list are front-loaded ahead of the auth and return-value notes. The unexplained 'v2 card' jargon costs it the top mark.

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 the return payload is optional (and it does so succinctly), and the auth prerequisite is covered. The fatal gap is that 16 of 21 input parameters have no semantics anywhere, which is a large incompleteness for a schema this wide.

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 21 parameters and 0% schema description coverage, the description carries the full burden, yet it names only 5 fields (confirm, not_when, principle, verify, rollback). The 3 required fields (title, problem, steps) plus cause, error, failed, technology, environment, variables and others are left completely undefined anywhere in the definition.

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 ('Contribute a reproducible fix') and names the artifact type ('v2 card'), which separates it cleanly from read siblings like get_fix and search_fixes. It stops short of explicitly distinguishing itself from the other write siblings (comment_fix, report_fix_result, report_outcome), which is the remaining ambiguity.

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?

'Contribute a reproducible fix' implies the trigger, and 'Fill confirm / not_when / principle / verify / rollback' hints at the expected content shape. However, there is no explicit when-to-use vs when-not guidance, and no routing against the sibling reporting tools that also write fix-related data.

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