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

Annotations already declare readOnly=false, idempotent=true, and destructive=false, and the schema's idempotencyKey text explains replay semantics, so the safety burden is carried. The description adds real value by flagging that the outcome is *user-reported* rather than verified and that recording does not trigger submission/certification, but it says nothing about permissions, side effects, or what happens on an invalid outcome after recording.

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, no filler, scope stated first and the disambiguating exclusion second. Nothing redundant with the name or annotations.

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 6-parameter mutation with no output schema and low schema description coverage, the description covers intent and negative scope but omits most parameter meaning, error behavior, and any return/effect signal. Adequate as a minimum, but an agent still has gaps before calling it correctly.

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 only 33% (projectId and idempotencyKey), leaving outcome, feedback, reasonCode, and submissionSnapshotId undocumented. The description names only two of these ('outcome', 'buyer feedback') with no added syntax or constraints, and gives no guidance on reasonCode or submissionSnapshotId, so it does not compensate for the coverage gap.

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+resource ('Record a user-reported dossier outcome') plus the optional feedback artifact, and the negative clause rules out the submit/approve siblings. It does not explicitly distinguish itself from the similarly-named read-side sibling helvabase_outcomes, but the write verb 'record' carries that distinction implicitly.

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?

The exclusion 'Does not submit a dossier or certify approval' usefully separates this from the confirm_/submit_ family, but there is no positive statement of when an agent should call this versus helvabase_outcomes or the decision-confirmation tools. Usage is only implied by the tool name.

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