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

Annotations only mark the call as readOnly=false and idempotent=false; the description carries behavioral weight: missing probeSpec is rejected with error=probe_required, probeSpec alone implies post-deploy, the linter blocks high-severity issues in Grove mode, and the call returns criterion fields plus quality findings. No contradiction with annotations.

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?

Dense but every sentence carries operational value; the core action and constraint are front-loaded, and the example is small. No filler or repetition of schema fields.

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?

Covers validation, mode/lifecycle restrictions, linter behavior, and return payload despite having no output schema. The only minor omission is explicit handling of position, but schema already documents it, so nothing critical is missing.

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 coverage is 100%, so baseline is 3, but the description adds cross-parameter semantics: text must be observable, post-deploy requires probeSpec, omission triggers a specific error, and passing probeSpec alone sets probeClass=post-deploy. These rules are not inferable from individual parameter schemas.

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?

Opens with a specific verb and resource: 'Append an acceptance criterion to a goal,' which clearly separates it from sibling add-note/add-evidence/add-assumption operations. The rest sharpens the purpose by defining the content rules for an acceptance criterion (observable check, not subjective approval).

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 decision context: pre-merge vs post-deploy, when probeSpec is mandatory, and mode-specific constraints (Grove blocks after start, standard allows edits until close). It does not explicitly route to sibling update/remove tools, but the append-vs-modify distinction is evident from the operation itself.

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