Comment on PR

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, and the description usefully adds cost/latency ("one provider API call (issue-comments, or review-comments for inline notes)") plus the exact returned fields (repo, pr, inline, comment_id, url, created_at, body_chars). It stops short of stating auth/scopes required to comment or whether a posted comment can be edited or removed, which is the remaining gap for a non-idempotent write tool.

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?

Front-loaded with purpose, then labeled Use/Avoid/Speed/Output/Batch-safe blocks, so an agent can scan to the relevant line. It is slightly longer than necessary because the inline-note mode is restated three times (purpose, Use-when, and again in Output), but nothing is padding.

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 10-parameter, no-output-schema write tool, the description supplies what the structured fields cannot: when to use it, what it returns, per-call API cost, and batching posture. Provider/repo/commit defaulting is left to the schema, which documents it fully, so nothing an agent needs to invoke correctly 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 description coverage is 100%, so the schema already does the heavy lifting and baseline is 3. The description adds meaning on top by surfacing the cross-parameter dependency ("pass path + line" for inline notes) and the number-vs-URL acceptance for `pr`, which are the two combinations most likely to be mis-invoked.

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 ("Post a comment on a pull request") and immediately distinguishes its two modes: a general thread comment versus an inline review note pinned to file/line. It also states the accepted identifier forms (PR number or full PR URL), so an agent can tell exactly what this does without opening the schema.

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?

Explicit "Use when" and "Avoid when" clauses cover both the reporting/answering cases and the inline-note case, and it names a concrete alternative for the wrong-tool case ("you want to change code (use project_edit_file)"). The precondition "PR is not open yet (create it first)" is an actual exclusion, not a vague hint.

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