Fibre Compare

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is fully covered. The description adds the external-service dependency and what a result contains, but says nothing about rate limits, throttling, error cases when a postcode is invalid, or coverage gaps — modest added value on top of the annotations.

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 the core action and scope, with filters last. Slightly padded by enumerating return fields (providers, speeds, prices, contracts, features, sign-up link) that the output schema already supplies.

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 an output schema present and full schema coverage for 12 parameters, the description need not explain return structure, and it correctly covers scope and filters. Its main omission is the multi-call workflow implied by visitor_id/address_key (reuse across calls), which an agent must infer from the schema alone.

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 100%, so baseline is 3. The description echoes postcode, UPRN/UDPRN and the four filter dimensions but adds no syntax, defaults, or behavior beyond what each schema property already documents (including the nuanced visitor_id/address_key chaining, which only the schema explains).

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 precise verb and resource ('Check which fibre and broadband deals are available'), bounds it geographically (UK postcode), and names both the identifier modes (postcode vs UPRN/UDPRN) and the backing service (fibrecompare.com). This is specific enough that an agent can distinguish it from the generic 'fetch'/'search' siblings 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?

Gives clear context: postcode-level by default, address-level when a UPRN/UDPRN or matching address is supplied, plus the optional filter dimensions. It does not state when NOT to use it or name which sibling to prefer for, e.g., looking up a single known deal, so it stops short of full routing guidance.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered by structured data. The description adds only the dependency on search-issued ids and the 'compatibility tool' framing; it offers no further behavioral detail such as error behavior for unknown ids or what 'full details' comprises.

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 tight sentence with no filler; the pairing constraint and the retrieval action are both stated in one pass, and nothing is redundant.

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 one fully documented parameter, a complete annotation set, and an output schema that handles return values, the description covers what an agent needs to invoke it correctly. Only marginal enrichment (error cases, id provenance edge cases) is absent, which is acceptable at this complexity.

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?

There is a single parameter fully documented in the schema (100% coverage), including the '<postcode>|<product_id>' format, so the schema carries the semantics. The description echoes the id's provenance from search but adds no format or validation detail beyond it, making 3 the correct baseline.

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 gives a specific verb (retrieves), a precise resource (the full details of one broadband deal), and the scoping mechanism (by its id, from results returned by search). This distinguishes it cleanly from sibling `search`, which returns the list, without the agent needing to open either 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 states the tool is paired with `search` and operates on a deal id that search returned, which clearly signals the intended call sequence (search first, then fetch). It stops short of an explicit when-not-to-use statement or naming `check_fibre_availability` as an alternative, so it falls short of a 5.

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

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

Annotations already cover read-only, open-world, idempotent and non-destructive traits, so the bar is lower. The description adds real context beyond them: it is a compatibility shim forced by search/fetch-style clients, it targets a specific external site, and its output feeds the fetch sibling. It does not mention rate limits or pagination, but the output schema covers returns.

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?

Compact — two sentences that each carry load. The client-compatibility caveat comes first rather than the core action, so it is not perfectly front-loaded, but there is no filler and no redundancy.

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 one-parameter read tool with full annotations and an output schema, the description supplies everything an agent needs: the compatibility rationale, the preferred alternative, the target source, and how results connect to fetch. Nothing material 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?

Schema coverage is 100% for the single parameter, and the schema already documents that the string is free text containing a UK postcode with examples. The description repeats "a UK postcode contained in the query" without adding parsing rules or format constraints, so the baseline 3 is appropriate.

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?

State a specific verb and resource: "Searches fibrecompare.com for broadband deals available at a UK postcode." It also distinguishes itself from both siblings by naming check_fibre_availability as preferred and explaining that results are "deal ids for fetch," so an agent can place it in the workflow without opening any 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?

Explicitly scopes when to use it ("Compatibility tool for clients that require search/fetch, e.g. ChatGPT deep research") and when not to ("Prefer check_fibre_availability"). Both the routing condition and the exclusion are stated, leaving nothing to inference.

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