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

Goes well beyond the destructiveHint/idempotentHint annotations: rotate's new secret is shown ONCE and must be handed to the user, the old one immediately stops working (irreversibility made concrete), set enforces 16-256 chars with no spaces, and the operation is owners-only. That is exactly the operational context an agent cannot infer from structured fields.

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 what the tool does, then splits rotate vs set into scoped clauses, then names the endpoint source and the permission requirement. Telegraphic but every clause carries unique information; nothing is repeated from the schema.

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?

For a 4-param mutation with no output schema, the description covers the irreversible consequence, the one-time display of the returned secret, input constraints, prerequisite listing tool, and authorization level. Nothing needed to call it 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 3 is the baseline, but the description adds real meaning: `secret` is only for set (not rotate), its length/charset constraints, and the provenance of `endpoint` from list_form_webhooks. It does not clarify why `id` (site id) is present alongside `endpoint`.

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 pair (rotate/set) and the exact resource — the webhook signing secret for a form, with the header and algorithm named. 'Form webhook' distinguishes it from the sibling set_collection_webhook without the agent needing to open either 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?

The description disambiguates the tool's own two modes: rotate when PageHub should mint a new secret, set when storing a receiver-issued secret. It also tells the agent where `endpoint` comes from (list_form_webhooks). It does not explicitly rule out the collection-webhook sibling, but the resource naming makes the boundary clear.

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