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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world behavior, so the safety profile is fully covered and the description only needs to add context. It adds the important detail that an empty state means 'all', but says nothing about result shape, ordering, or size, and its 'optionally filtered by version' wording contradicts the schema's required list.

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 short sentences, front-loaded with the core action and immediately followed by the state enumeration; no filler. The only cost is the misleading 'optionally filtered' clause, which spends words on a claim the schema contradicts.

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 annotations covering safety, the remaining burden is the two required parameters and the missing output schema, and the description half-addresses that by defining state values. It leaves the version parameter's format and the returned fields/ordering unexplained, so an agent can call it but cannot predict the response shape.

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, and it does enumerate the four legal 'state' values (including empty = all), which the bare string schema lacks. However, it gives no format for 'version' (exact string, prefix, latest?) and describes it as optional when the schema requires it, leaving an agent unsure what to pass.

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 gives a specific verb ('List') and resource ('planned/implemented/rejected design docs') plus a filtering dimension, so an agent knows exactly what the call returns conceptually. It does not name or rule out the singular sibling 'design_doc' or 'docs_search', leaving the boundary to be inferred from the names alone.

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?

Usage is implied: use it to enumerate docs, pass an empty state for all, and narrow by version. There is no explicit when-to-use versus when-not guidance (e.g., versus fetching a single doc with 'design_doc' or searching with 'docs_search'), and the claim that version is an optional filter conflicts with the schema marking it required.

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