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

Annotations already indicate a write operation (readOnlyHint=false) and non-destructive behavior (destructiveHint=false), which the description's 'add a comment' aligns with. The description adds value beyond annotations by disclosing the side-effect 'Notifies the team' and clarifying the threading model ('annotation's thread'), details not present in the structured metadata.

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 (22 words) that front-load the verb and resource in the first phrase. The first sentence conveys the action and purpose; the second conveys a side-effect. No filler, redundancy, or unnecessary detail.

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 2-parameter mutation tool with an output schema, the description covers the core essentials: what it does, an example use, and a side-effect. The output schema handles return values, and annotations cover the safety profile. It could note that the annotation must exist or explain invalid-input behavior, but that is an edge detail for a simple tool.

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?

The schema documents 'body' with 'The comment text' (50% coverage), but 'annotation_id' only has a type with no description. The description's reference to 'an annotation's thread' provides minimal semantic context for annotation_id — that it identifies the annotation whose thread receives the comment — but this does not fully close the parameter documentation 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?

The description clearly states the operation ('Add a comment') and the target resource ('an annotation's thread'), making the action unambiguous. The example 'e.g. to record what you changed' adds concrete intent, and the verb-plus-resource combination distinguishes it from sibling read-only tools like list_comments.

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 example 'e.g. to record what you changed' provides a clear scenario for when to use the tool, implying context such as recording changes on an annotation. However, it does not explicitly name alternatives or state when not to use it, so it stops short of full usage guidance.

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