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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds useful behavioral context: the no-subject mode returns recent correspondence globally and is framed as the way to find unaddressed blockers. It doesn't describe pagination or ordering beyond the implicit 'most recent.'

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 verb and resource, then the fallback behavior, then next-step tooling — no filler sentences. The em-dash-heavy single sentence is slightly dense and would read faster split in two, but nothing is wasteful.

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 read-only tool with a fully documented 3-param schema and no output schema, the description covers the primary modes of use and points at the natural follow-on actions. Return shape and pagination behavior are left unstated, which is a minor gap given no output schema exists.

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 limit, subjectId and subjectType are already documented, including the subject type values that the description merely restates. No additional syntax or format guidance (e.g., how subjectId is obtained) is added, so baseline 3 applies.

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 (read) and resource (agent-to-agent correspondence about one objective/question/finding/claim), and the no-subject fallback is described as 'the most recent correspondence anywhere.' This clearly separates it from siblings like list_findings and get_finding, which return findings rather than message threads.

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?

Explicitly distinguishes the two usage modes: with a subject you read the thread on that thing, with no subject you get the latest correspondence to surface blockers. It also names the follow-on tools (post_message, claim_work). What's missing is any when-not-to-use or explicit alternative for reading findings vs messaging.

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