Ampworth documents

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

Annotations already declare the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds genuinely useful context: Markdown output, embedded MCS provenance, linked calculator ids, and per-question return shape for Q&A documents.

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?

Core purpose and format are front-loaded in the first sentence, and the workflow hint follows immediately. The closing citation rule is legitimate guidance but drifts from invocation and adds a third paragraph of modest value.

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 single required-parameter read tool with an output schema and full annotation coverage, the description supplies more than enough: purpose, source of the slug, output format, and content shape. Nothing needed to invoke it 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?

Schema coverage is 100% and the schema's own slug description already states 'from search_documents or list_documents. Required.' The description merely restates that, adding no syntax, format, or validation detail beyond the structured field. Baseline 3 applies when the schema does the work.

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 ('Fetch the full text of one guide, article or set of questions by its slug') and adds the output format ('as Markdown, not HTML'). By positioning list_documents/search_documents as slug sources, it implicitly distinguishes itself as the retrieval step in the workflow.

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?

Clearly routes the agent: slugs come from search_documents or list_documents, so this tool is used after one of those. No explicit when-not or exclusion condition is given, but the sequencing context is unambiguous.

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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is fully covered. The description adds content-shape context (guides are shelved by perspective, first four plain-language, 'learning' carries methods and citations) but adds nothing behavioral beyond that, and return format is covered by the output schema.

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 core action and then usage, which is good ordering. However, the perspective enumeration is repeated verbatim in the schema, making the middle of the description somewhat redundant rather than earning 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?

With an output schema present, return values need not be explained, and the description covers purpose, filter dimensions and usage context adequately. It leaves minor gaps around result volume/pagination, but nothing that would prevent correct invocation.

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 the schema already documents all four filters, including the perspective values. The description largely restates the same perspective/category semantics the schema provides, so it adds little new parameter meaning beyond the 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 states a specific verb and resource ('Lists every document') plus the optional filter dimensions, and it is clearly separable from search_documents through the phrase 'before searching, or when a search returned nothing'. An agent can tell what enumeration means here 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 when-to-use conditions against the search sibling ('to see the shape of what is covered before searching, or when a search returned nothing'). It does not name get_document or state when not to use this tool, so it falls just 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 readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuine context beyond that: results are summaries only, a matching embedded question returns with its answer, and coverage is limited to the UK.

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 core action and the 'use first' instruction, then follows with return behavior and scope. Slightly redundant in restating the UK-only coverage in the first and last sentences.

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, the description need not explain return values, yet it still clarifies that results are summaries and that get_document reads full text. Usage conditions, alternatives and geographic scope are all covered.

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 the schema already documents both query and limit fully. The description adds no syntax or format detail for the parameters, so the baseline 3 applies.

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 (search) and resource (guides, articles, questions) and scopes the subject to UK home energy. It routes to the sibling get_document for full text, but does not explicitly distinguish itself from list_documents.

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 says to use this first before answering from memory, and enumerates concrete triggering question types (system sizing, standards, quotation contents, planning permission, figures on quotations). It also names the alternative get_document and when to follow up with it.

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