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

Annotations only cover safety flags, and the description adds genuinely useful behavior: the first check stores findings without alerting, every page read and match check is billed to the account's usage, and a free SnoopScan key is required. It stops short of describing failure behavior, what happens to omitted fields during an update, or how alerts are later delivered.

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, then parameter meanings, then operational caveats and the key requirement — sensible ordering with no filler. The middle parameter dump is dense and semi-colon chained, which makes it slower to scan than it needs to be, but every clause carries information.

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 14-parameter create-or-update tool with an output schema and no required fields, the description covers the create/update switch, cost model, key requirement, and silent first run. The remaining gap is update semantics: it says 'the fields to change' but never confirms that omitted fields are preserved rather than cleared, and `active`/`includeUnknownLocation` go unexplained.

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 0% across 14 parameters, so the description carries the burden and largely does: it explains `query` as plain words, prices as whole pounds, postcode+radiusMiles as a distance limit, includeDelivery as extending that limit, sites defaulting to all, and intervalMinutes bounded 60–1440 with default 360. Two parameters, `active` and `includeUnknownLocation`, get no explanation at all and there are no enums to lean on.

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 concrete verb+resource: it saves a scheduled 'item hunt' that checks named marketplaces (eBay, Gumtree, Preloved, Vinterior, The Saleroom, Etsy) for sale listings and keeps only real matches. The create-vs-change duality is spelled out (name+query to create, watchId to change), and it routes reads to `listListings`, so an agent can place it against siblings 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?

Explicit creation condition (give `name` and `query`) and modification condition (`watchId` plus the fields to change), plus a pointer to `listListings` for reading results. It does not explicitly say when not to use it or name alternatives such as watchMentions/watchPages for mention or page monitoring, so the guidance is clear but not exhaustive.

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