list_annotations

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description goes beyond that by disclosing two non-obvious behaviors: pagination is bounded, and errors are reported per-record rather than failing the whole call. It also confirms reading has no resolve side effect, which matters given a sibling named resolve_annotation.

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 tight sentences with zero filler; the resource and the scope constraint are front-loaded before the side-effect clarification. 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?

An output schema exists, so return values need not be explained, and the pagination/partial-failure model is stated. The gap is on the input side: with 0% schema coverage and a status filter, the definition leaves an agent guessing about the semantics of open vs resolved vs all.

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 0%, so the description must carry parameter meaning, but "bounded pagination" only loosely gestures at limit and cursor and never states the upper bound. The status enum (open/resolved/all) — the most semantically important filter — and projectPath are left entirely unexplained by both schema and description.

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 ("Read submitted immutable annotations") and adds the distinguishing property that these are immutable submissions read with bounded pagination. It implicitly separates itself from resolve_annotation via "Reading never resolves records," though it never names the sibling that fetches a single annotation.

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?

"Reading never resolves records" implies that mutation of annotation state belongs to a different tool, which is useful routing. However, there is no explicit guidance on when to use this bulk listing versus get_annotation or get_annotation_status, and no exclusion criteria are stated.

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