register_brand_audit_watch

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the description's burden is lower. It adds value by disclosing that each run enqueues a batch, optionally POSTs a webhook on drift, returns a watchId, and has a per-principal cap. No contradictions with annotations.

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?

Four sentences, each earning its place: purpose, runtime behavior, return value, and constraints. Front-loaded with the core action, no fluff, well-structured.

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?

Given the presence of an output schema and three well-documented parameters, the description covers all necessary aspects: creation, recurrence, enqueuing, webhook, return, and limits. No gaps identified.

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?

All three parameters have schema descriptions, so baseline is 3. The description adds useful context for 'webhook_url' (SSRF re-validation at both register and delivery) and reinforces the interval's recurrence nature. This exceeds the baseline.

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 description uses a specific verb ('Creates') and resource ('recurring brand-audit watch') with clear details on cadence (daily/weekly/monthly) and runtime behavior (enqueues brand_audit_batch_start, posts webhook on drift). It distinguishes well from siblings like brand_audit_single (one-time) and list_brand_audit_watches (listing).

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 provides clear context for when to use this tool (recurring monitoring) and includes constraints (owner-scoped, cap of 20 watches). It does not explicitly contrast with alternatives like one-time audits or other tools, but the mention of recurring cadence and cap gives sufficient guidance.

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