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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds behavior the annotations do not: a hard cap of the last 100 messages, chronological 'newest last (reading order)' ordering, and the 'read tier' permission requirement. What it omits is anything about the shape of an individual message beyond created_at.

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-loads the core purpose and route, then the return set, then the optional filters, then the sibling pointer. Dense but essentially waste-free. It is a single run-on sentence plus fragments, which slightly reduces scanability, but every clause carries information.

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 no output schema, the description must carry the return contract, and it does: entry kinds, the 100-message cap, and ordering. The created_at reference implies message timestamps. What is missing is the per-message field set (id, author, kind) an agent would need to parse results, which is the only real gap for a read tool of this complexity.

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 kinds and since parameters are already fully documented in the schema (including the note/discussion aliasing and the pass-created_at pattern). The description largely restates that semantics rather than extending it, apart from tying since to the 'last message you saw' workflow. Baseline 3 is appropriate when the schema does the heavy lifting.

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 and resource ('Read a task's trail messages'), names the underlying protocol entity and HTTP route, and enumerates the entry kinds returned (question, answer, handoff, note/discussion). It also names the sibling that performs the opposite operation ('Post with tascan_post_message'), so the agent can separate this read tool from tascan_get_task and tascan_post_message without opening a 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?

Gives concrete usage context for both optional parameters: use kinds to narrow to a comma-separated set, and use since with the created_at of the last message seen for incremental reads. It also routes writes to tascan_post_message. It never states when not to use it (e.g. versus tascan_get_task for metadata), so it stops short of full when/when-not guidance.

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