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

With no annotations, the description carries the full burden, and it does disclose meaningful traits: it is a pure offline lookup, requires no API key/auth, and preserves leading zeros. It stops short of stating what happens for an invalid or unknown code, which is the one behavioral gap.

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 purpose in the first sentence and the example immediately after; almost every sentence earns its place. The trailing "Args:" block partially restates the format already given above, which is mild redundancy rather than bloat.

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-argument lookup with an output schema present, the description is largely complete — the output schema handles return values and the description still adds a sample mapping. The only thin spot is invalid-code behavior, which neither the description nor the schema covers.

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 0% with one parameter, so the description must compensate, and it does: it gives the expected format (5-digit, example "43220") and explicitly notes that leading zeros are kept — a real semantic detail given the string type. Missing only validation/error semantics for malformed input.

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?

Specific verb ("Decode") plus specific resource ("UK SIC code"), with the domain role spelled out ("the 5-digit 'nature of business' code on every company record"). It is unmistakable against siblings search_companies, get_company, and get_filing_history, and the worked example removes any ambiguity about output.

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 situates the tool in the company-record workflow (SIC codes appear on company records) and states the operational context: works offline, no API key needed. It does not explicitly name siblings or say when NOT to use it, but the alternatives are not plausibly confusable, so the implicit guidance is sufficient.

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?

No annotations are provided, so the description carries the full behavioral burden, and it discloses very little beyond content: no auth/permission requirements, no rate limits, no note on whether a dissolved company's record behaves differently, and no indication of what happens on an unknown number. 'From its official registry record' hints at the data source, which is the only real behavioral signal.

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 resource and scope, followed by a compact args block; both sentences of the summary earn their place. The field enumeration slightly duplicates the existing output schema, but the overall size is appropriate for a one-parameter tool.

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 simple one-parameter lookup with an output schema, the calling essentials (parameter format) are covered, and return structure need not be explained. However, the absence of any when-to-use or sibling-routing guidance leaves a real gap given three related siblings, and the return-field list partly re-describes what the output schema already holds.

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%, so the description must compensate, and it does well: it specifies the 8-character Companies House number format, gives four representative examples including SC/NI prefixes, and notes that leading zeros are optional. That is exactly the format detail the bare string schema lacks.

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 resource and scope — the full profile of one UK company from its official registry record — and enumerates the fields returned (status, incorporation date, registered office, SIC codes, officers). This implicitly separates it from the list-oriented search_companies sibling, but it never names or contrasts any sibling explicitly.

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?

There is no when-to-use guidance, no prerequisites, and no routing advice such as 'use search_companies to resolve a company number first'. The agent must infer from the name that this is a single-record lookup and that explain_sic_code / get_filing_history exist for adjacent tasks.

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?

With no annotations, the description carries the full burden. It usefully discloses the return content ('most recent' ordering and the filing types returned), which is genuine behavioral context. However, it says nothing about permissions, rate limits, or result volume/pagination behavior beyond the page-size parameter.

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 purpose, then usage context, then Args — a clean and skimmable structure. The parenthetical example lists add some length but earn their place by clarifying scope.

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 needn't be spelled out. For a simple two-parameter read tool the description covers purpose, triggers, and parameter formats adequately; only pagination/ordering details are thin.

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%, so the description must compensate, and it does: it explains company_number accepts leading zeros optionally and gives the items_per_page range (1-100) — details absent from the schema. Both parameters receive meaningful documentation, though deeper format/validation guidance is limited.

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: retrieves 'the most recent filings a company has made at Companies House', with concrete examples (confirmation statements, accounts, officer changes). This clearly distinguishes it from get_company (company details) and search_companies without needing to open 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?

Gives clear when-to-use context ('spotting dormancy, late accounts, or a change of directors last week'), which tells the agent the practical triggers for calling it. It does not explicitly name alternatives or exclusions, so it falls short of the top tier but is well above mere implication.

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?

No annotations are provided, so the description carries the full burden. It does useful work by naming the returned fields (number, status, address snippet, incorporation date), which tells the agent this is a non-destructive read and what to expect. However, it says nothing about result ordering/'best match' semantics, rate limits, or pagination beyond the page size.

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 return shape, then a compact Args block. Every sentence is useful; the Args block is minimally redundant with the schema but serves as a fallback given zero schema descriptions.

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 simple two-parameter search with a sibling for follow-up lookup, the description covers purpose, return fields, and the hand-off to get_company. Since an output schema exists, return values need not be detailed, and the remaining gaps (ordering, no-match behavior) are minor.

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%, so the description must compensate, and it does: 'query' is explained with concrete examples ('Driver Plumbing', 'TESCO') and 'items_per_page' gets a range and default (1-100, default 10) that the schema itself omits. Only the integer type/format nuance is left implicit.

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 ('Search the UK company register by name') and lists the returned fields, so the agent knows exactly what comes back. It also distinguishes itself from the sibling get_company by explaining that this is the name-lookup entry point.

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 routes the agent forward: 'use the company_number from the best match with get_company.' That is a clear when-to-use chain, but there is no exclusion guidance (e.g., what to do if no match is found, or when to skip straight to a number lookup).

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