Ampworth documents

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

Annotations already declare readOnly, idempotent and non-destructive behavior, so the safety profile is covered. The description adds real behavioral value beyond them: the output is Markdown not HTML, the response carries MCS source documents and calculator ids, and question-sets return Q&A separately.

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-loads the core action in the first sentence, then layers return-shape and citation guidance. Every sentence carries information, though the final citation instruction is advisory rather than operational and slightly dilutes focus.

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-parameter read tool with an output schema and full safety annotations, the description covers what is needed: what it returns, in what format, and how to obtain the required slug. Nothing an agent needs 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 parameter description already says 'from search_documents or list_documents. Required.' The description repeats the slug provenance but adds no syntax, format, or edge-case detail beyond the schema, so 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 and resource: fetch the full text of one guide/article/question-set by slug. It distinguishes itself from siblings by noting slugs come from search_documents or list_documents, so an agent can tell retrieval-by-id apart from listing/searching.

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?

The description makes the workflow explicit by telling the agent the slug must come from search_documents or list_documents, which effectively routes discovery through the siblings. It stops short of stating when not to use it (e.g., when only metadata is needed), so it is clear context rather than full when/when-not 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 and destructiveHint=false, so the safety profile is fully covered without description help. The description adds that the listing is exhaustive ('every document') and that filters are optional, but says nothing about pagination, result volume, or auth needs — modest added value on top of rich 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?

Front-loads the core verb and resource, then layers filters and usage in a single tight paragraph with no filler sentences. The perspective enum list and the 'first four are plain language' clause duplicate what the schema fields already say, which is mild redundancy but does not bloat the text.

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?

Output schema exists, so the description is not obliged to describe return values, and it covers what remains: scope of the listing, optional filters, domain-specific filter semantics, and when to prefer this over searching. Nothing an agent needs 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 description coverage is 100%, and articles/guides-only constraints plus enum meanings are already documented per-field in the schema. The description largely restates the 'perspective' and 'level' values, adding interpretation ('match the reader') but little syntax or format detail the schema lacks. Baseline 3 is correct.

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 ('Lists') plus resource ('every document') and immediately scopes it with the available filters. The final sentence implicitly distinguishes it from search_documents by positioning it as the browse-the-shape tool rather than the lookup tool, so an agent can route correctly.

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 explicit when-to-use guidance: 'before searching, or when a search returned nothing' — the second clause is a genuine fallback rule that names the sibling's failure mode. It also instructs how to pick filter values ('Match the perspective to the person asking'), which is actionable selection guidance rather than vague context.

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, closed-world, but the description adds behavior the schema and annotations cannot: results are summaries rather than full documents, matched sub-questions return inline with their answers, and coverage is limited to the United Kingdom. These are real operational facts an agent needs before calling.

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 purpose and the primary usage directive, and each paragraph carries a distinct fact (scope, follow-up tool, inline Q&A, geography). The closing two sentences about UK coverage slightly restate the opening scope, costing a little tightness.

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 structure need not be spelled out, and the description still covers the essentials: what the corpus contains, what results look like at a high level, the follow-up path, and the geographic boundary. Nothing needed to call 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%, so both the query and limit parameters are already documented in the schema, including 'plain words work best' and the 1-25 range. The description adds no syntax, format, or ranking detail beyond that, 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?

Names a specific verb and resource ('Search the guides, articles and questions') and scopes the corpus to UK home energy subjects. It also distinguishes itself from the sibling get_document by stating that searching returns summaries and get_document reads one in full.

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, enumerates the question types it covers (sizing, standards, quotations, planning permission), and routes the agent to get_document as the follow-up. That is close to a complete when-to-use instruction.

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