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

Goes well beyond the annotations by disclosing the per-principal cap of 20 active watches, owner scoping, the side effect that each run enqueues a fresh brand_audit_batch_start, webhook emission on classification drift, and the returned watchId. These are non-obvious operational traits (quota, blast radius, async fan-out) that annotations alone cannot convey.

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?

Three tight sentences, front-loaded with the create action and cadence, followed by side effects and then constraints. Every clause carries distinct information (trigger, webhook behavior, return value, quota) with no repetition of schema text.

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 non-destructive but state-creating tool with no output schema, the description covers what is created, what happens on each run, the return value (watchId), ownership scope, and the quota ceiling. An agent has everything needed to decide to call it and to predict the outcome.

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 100%, so domain, interval, format, and webhook_url are already fully documented, including SSRF re-validation on the webhook. The description only restates cadence options and webhook presence, adding no syntax or default behavior beyond the schema — baseline 3 is appropriate.

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 ("Creates a recurring brand-audit watch for a domain") plus the cadence dimension, which immediately separates it from list_brand_audit_watches and delete_brand_audit_watch. An agent knows this is the creation entry point for scheduled audits without opening the 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?

Gives clear conditions for use — recurring daily/weekly/monthly auditing of a domain — and names the chain it triggers (brand_audit_batch_start per run), which implicitly routes one-off work to the single-scan siblings. It stops short of an explicit exclusion sentence such as "for a one-off scan use brand_audit_single," so it is clear context rather than full routing.

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