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

With annotations already declaring readOnly/openWorld/idempotent/non-destructive, the description still adds real behavioral context: the data source (Home Office register), what is returned (town, licensed visa routes, register date), and the important caveat that a licence lets an employer sponsor but each job must still qualify. It omits what a no-match result looks like.

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 question it answers, then progressively the data source, caveats, and fallback strategy. The closing OGL attribution sentence is boilerplate but short and legally required; everything else earns its place.

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?

There is no output schema, so the description correctly supplies the return shape (town, licensed routes, register date) plus the licence-vs-job nuance. Only minor gaps remain, such as behavior on an unknown employer or name-matching ambiguity.

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% for the single company parameter, so baseline is 3, but the description adds genuinely useful guidance beyond the schema: register names are legal names, so retry with the legal name if the brand name fails. That is actionable lookup strategy, not repetition.

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+resource (looks up employer in the UK Home Office register of licensed sponsors) and frames it around the exact user question it answers. This is clearly distinguishable from data-provider siblings like jobspotter_search_jobs or jobspotter_company_lookup, which do not touch the sponsor register.

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?

Example user phrasings ('does Deliveroo sponsor visas?') make the triggering intent explicit, and it routes US-job questions away to the visa_sponsorship field on search results. It does not name a sibling tool for that alternative case, so it stops just short of a full when/when-not map.

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