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

Adds real behavioral context beyond the annotations: batch edits are bounded, one result is returned per requested item, and partial failures must be surfaced rather than reporting the whole batch as successful. The annotations only say readOnly=false, destructive=false, idempotent=false, so this partial-failure contract is genuine added value. Minor gap: it doesn't clarify permission or auth requirements.

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 action statement followed by trigger, exclusion, and batch/result semantics. Every sentence earns its place with no filler.

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?

An output schema exists, so return values need not be explained, and the description covers triggering, the delete alternative, batch bounds, and partial-failure reporting. The only residual gap is the absence of parameter-level detail to compensate for the 50% schema coverage.

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 50%; the description only vaguely maps to the two modes ('create' vs 'set_status') without naming the operations array, companyId, watchId, or status fields. The anyOf schema itself documents the mode structure, so the description adds little beyond what structured data already provides.

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 ('Create company employee watches or change their active/paused state') and explicitly names the sibling operation it is not ('does not delete watches; use campaignstack_delete_company_employee_watch'). An agent can distinguish it from related edit/delete watcher tools without opening schemas.

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 an explicit trigger ('when the user asks CampaignStack to watch a company for new hires or pause/resume an existing company watch') and an explicit exclusion with the named alternative tool for deletion. Nothing is left to inference.

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