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

Annotations already declare readOnly, idempotent, non-destructive and openWorld=false, but the description adds real behavioral context beyond them: it is a published national average with no applicant, product or lender attached, it is an appraisal input rather than a quotable rate, and it is free. That framing prevents a category of misrepresentation the annotations say nothing about.

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 short paragraphs, front-loaded with what the data is, then how to use it, then the mechanical facts (no params, free). No sentence is redundant with another and nothing is buried.

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 no explanation. Scope (UK, national), data provenance (BoE), the specific series covered, the absence of parameters, and the recommended pairing are all present; nothing an agent needs to call this correctly is missing.

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?

With zero parameters the baseline is 4, and the description justifies the empty schema ('one national series'), which explains why no filtering arguments exist. It does not go further into what distinguishes each published series or its update cadence, so it stays at the baseline rather than exceeding it.

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 (average UK mortgage rates from the Bank of England) and enumerates the exact series returned: 2-year fixed, 3-year fixed at 75% LTV, and SVR. An agent can distinguish this from sibling series tools like market_yields or asking_price_index_series 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?

Explicit when-not guidance: 'do not present it as a rate someone can get,' plus a positive routing instruction to pair it with a yield figure or `site_appraisal`. This names both the misuse mode and the alternative consumer of the output, which is exactly what an agent needs to place the tool in a workflow.

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