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

With no annotations, the description carries the full burden and does well: it discloses poll cadence (hourly), the exact data sources polled, the notification mechanism (webhook on change), duration (30 days) and cost ($5.00 USDC). It omits lifecycle details such as what happens at expiry, whether renewal is automatic, webhook retry/failure behavior, and what happens if payment fails.

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?

A single dense sentence that front-loads the core action and packs cadence, sources, delivery and price without waste. The telegraphic style ('CH poll', arrow notation, '30d USDC') is efficient but slightly terse; a small amount of plain-language expansion would cost nothing.

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 paid, long-running watch job with no annotations and no output schema, the description covers the essentials an agent needs to decide and call: what is watched, how often, how changes are delivered, how long it lasts, and the cost. The notable remaining gap is the subscription lifecycle — what the call returns (a monitor ID?), cancellation/renewal, and expiry behavior.

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% — 'number' is a bare string and 'webhook' is only typed as a URI. The description does imply that 'number' is a UK company number and that 'webhook' is the destination for change notifications, which is real added meaning. But it gives no format expectation for the company number (e.g. Companies House 8-character format) and no requirements for the webhook (publicly reachable, HTTPS), which is what the zero-coverage schema most needs.

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 with scope and mechanism: 'watch one UK company 30 days' via hourly Companies House polling of status/officers/filings/PSC/charges with a webhook on change. This clearly separates it from one-shot siblings like uk_company or company_full, which return a snapshot rather than an ongoing watch.

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?

'Use this to watch one UK company 30 days' implies the use case (ongoing monitoring vs a one-time lookup), and the 30-day/price framing signals a paid subscription. However, no alternatives are named (uk_company, company_full, create_monitor, uk_dd) and there is no when-not guidance, so the agent must infer routing from the verb alone.

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