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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description does add context beyond them by naming the authorization model ('connected identity and existing ownership checks'), which tells the agent failures are permission-driven. It says nothing about what a denied read returns or how revisions behave.

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, zero filler, with the access constraint front-loaded before the sibling routing. The second sentence is slightly compressed to the point of ambiguity ('Public records use fetch' never defines 'public record'), but nothing is wasted.

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 and rich annotations carry much of the load, and the auth model is stated, so the minimum is met. For a tool with a revision parameter and a compact/full projection, the description should explain what choosing a revision or view implies; that is left entirely to the schema.

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 25%: 'id', 'kind' and 'revision' carry no description at all, and the description mentions none of the four parameters. 'revision' — presumably a version/optimistic-concurrency selector — is completely undocumented anywhere, which is the kind of gap the description is supposed to close.

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 network question') and scopes it to the connected identity, which separates it from the generic read siblings. The second sentence explicitly names the 'fetch' sibling, so an agent can tell the two apart. It stops short of 5 because it never says what a 'network question' is relative to the problems/solutions the other siblings operate on.

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 a positive condition (authorized content, connected identity and ownership checks) and a concrete alternative for the other case ('Public records use fetch'). That is real when-to-use routing. It lacks an explicit when-not for the remaining siblings (search, fetch_anonymous_knowledge), so it is clear context rather than a full decision rule.

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