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

Annotations declare destructiveHint=true and non-idempotent, and the description earns that: rotating means 'the old stops working' and the new secret is 'shown once'. It also discloses the runtime behavior the agent needs — senders POST rows to the ingest URL and rows upsert by externalId — which no structured field conveys.

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-loaded with the core action and free of filler, but the telegraphic fragments ('Owner or agency.', 'get_collection shows the URL.') read as clipped notes rather than prose. Every sentence still carries information, so 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?

For a destructive, permission-gated mutation with no output schema, the description covers the conversion exclusion, the one-time secret reveal, upsert-by-externalId semantics, signing guidance being shown, and where to read the URL. An agent can call this correctly without further context.

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 the baseline is 3. The description goes further for the two non-obvious parameters: rotate implies a one-time reveal and immediate invalidation of the prior secret, and secret is clarified as 'the sender's own' rather than a generated value, resolving ambiguity the schema text alone leaves open.

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 opening sentence names a precise verb and resource: 'Make a collection a webhook feed, or rotate / set its signing secret.' It covers all three modes (convert, rotate, set) in one clause and is clearly distinct from siblings like set_form_webhook_secret and get_collection.

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?

It states the selection condition for each mode ('rotate:true mints a new secret', 'secret uses the sender's own'), names an explicit exclusion ('A collection syncing from Sheets/Airtable isn't converted'), a permission gate ('Owner or agency'), and routes to a sibling for the read path ('get_collection shows the URL').

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