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

Discloses auth behavior (401 on signed-out), error semantics ('an error means that slug has no agent'), the mutating side effect of claim, and privacy handling ('business data stays in the chat'). This fits the readOnlyHint=false annotation, since claim can mutate account entitlement, and adds substantial context beyond it.

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 purpose, then flows through the access branches with no filler sentences; every clause encodes a rule. The single dense paragraph and parenthetical nesting make it harder to scan than it could be, keeping it below a 5.

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 compensates by naming the JSON access field's possible values and the required response for each, plus error and privacy behavior. Nothing needed to call or handle the result correctly is missing.

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 coverage is 100%, so baseline is 3; the description adds real meaning for claim by tying it to user confirmation ('ask, and set claim true only after the user says yes'), which the schema only states more weakly. The slug parameter gets no elaboration beyond the schema example.

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 ('Agent playbook for one published use case, by slug') and implicitly contrasts with the library tools that 'stay public.' An agent can tell it fetches the actionable playbook keyed by slug, though the sibling it differs from (get_use_case, run_agent) is not named explicitly.

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 explicit conditional branches: signed-out → 401 so the client can open Sign in; each access state (full, free_claim_available, preview with reason upgrade, not_included) has concrete instructions, including when to stop. It also says to run on chat-attached files rather than upload, and to set claim=true only after the user confirms.

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