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

Annotations already declare read-only, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds context annotations cannot: the data source is the company's own case sample, the window is Jan 2025–Oct 2026, and results are 'mostly non-lucrative visas' — a material caveat about representativeness. It does not discuss sample sizes or freshness beyond the window, which keeps it at 4.

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 sentences, front-loaded with what the data is, then how to call it, then the default. The first sentence is long and packs provenance, date range, metric list and visa caveat together, but each clause carries information an agent would otherwise have to guess.

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?

With no output schema, the description correctly explains the return shape (median, 75th percentile, published wait per consulate) and the no-argument default. Minor gap: it doesn't say whether country_of_residence is required when a state/region is given, or what happens if both consulate and state are supplied.

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 67%, with the consulate enum undocumented, but the description supplies the routing semantics the schema lacks: either supply a consulate directly, or supply a state/region so the tool resolves the correct consulate. That relationship between the two lookup paths is the key semantic an agent needs and it is stated.

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 names a specific resource (Spanish consulate residence-visa processing times), the exact metrics returned (median days, 75th percentile, consulate-published wait), the data provenance (My Spain Visa's own decided cases, Jan 2025–Oct 2026) and the visa type covered. That is far more specific than any sibling (requirements, assessment, calculator), so an agent can route to it 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?

It gives explicit call modes: pass a consulate, pass a US state / UK region to resolve the consulate, or pass nothing for the overview. It does not name alternatives or say when *not* to use it (e.g. versus spain_visa_requirements), but the usage pattern for this tool itself is unambiguous.

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