list_pull_request_review_threads

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

Annotations declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful context about being a paginated GraphQL page and that content is untrusted repo data. It also reveals it returns a 'bounded first page' of comments, hinting at pagination behavior. However, beyond annotations, it doesn't disclose much additional behavioral detail.

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?

The description is a compact two-sentence block with a strong security-relevant closing note. It's front-loaded with the core purpose in the first sentence. No wasted words. Could theoretically add more parameter/usage detail, but what's there is efficiently written.

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?

With 7 parameters, only 14% schema description coverage, no output schema, and no annotations beyond read-only safety, the description carries a heavy burden it doesn't fully meet. It doesn't explain what 'resolution state' or 'permissions' actually get returned, how pagination works end-to-end, or what the relationship is between 'first' and 'commentsFirst'. The bounded-comments detail is helpful but the overall tool contract is under-specified for an agent to invoke 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 14%, so the description must compensate for parameter meaning gaps. The description mentions pagination (page, first, bounded first page) which maps to 'after' and 'first' params, and mentions resolution state and permissions which relate to the tool's output. However, it fails to explain several parameters including commentsFirst, hostname, and the meaning/value of pullRequestNumber beyond its schema definition. The description is too brief to fully cover 7 parameters.

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 verb (Read), the resource (pull request review threads), and specific details (resolution state, permissions, bounded first page of comment bodies). It distinguishes from sibling tools like list_pull_request_reviews and list_pull_request_review_comments by noting it's specifically about review threads rather than reviews or individual comments. The security note about untrusted data adds valuable context.

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 description implies usage for reading review threads but does not explicitly state when to use this vs. the very similar single-thread get_pull_request_review_thread tool, or when one would prefer list_pull_request_review_comments. There's no explicit when/when-not guidance or mention of alternatives, but the clarity of what it reads provides reasonable implied usage context.

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