get_companies_house_guidanceRetrieve approved Companies House / PSC / WebFiling guidance. PSC filings name individuals (trustees), never the Trust itself.
| Name | Required | Description | Default |
|---|---|---|---|
| topic | Yes | Guidance topic. Example: psc or webfiling |
| Name | Required | Description | Default |
|---|---|---|---|
| topic | Yes | Topic that was requested | |
| guidance | Yes | Approved GOV.UK title, URL, and summary |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, and non-destructive behavior, so the safety profile is clear. The second sentence adds a useful domain rule about PSC filings naming individuals rather than the Trust, but no additional operational behavior (e.g., output size, versioning, prerequisites) is disclosed.
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?
The description is compact and front-loads the core purpose in the first sentence. The second sentence is somewhat tangential but provides useful domain context that helps an agent avoid a likely mistake, so it earns 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?
For a single-parameter, read-only tool with an output schema, the description supplies the necessary guidance scope and topic examples. It lacks explicit sibling routing, but the first sentence's explicit domain coverage makes the tool reasonably self-contained.
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?
The schema already describes the single topic parameter with an example, giving 100% coverage. The tool description restates that guidance covers PSC and WebFiling, which aligns with the schema but does not add format detail, allowed values, or behavior beyond it. 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?
The description opens with a specific verb and resource in 'Retrieve approved Companies House / PSC / WebFiling guidance.' The scope clearly distinguishes this from sibling tools like get_hmrc_guidance, and the PSC/WebFiling topics further narrow the definition.
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?
Usage context is implied by the tool's scope: use when retrieving Companies House, PSC, or WebFiling guidance. However, the description does not explicitly mention when to prefer this over get_hmrc_guidance or other sibling guidance tools, nor does it state exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool occupies a distinct step in the intake-to-submission pipeline, with clearly paired tools like prepare_submit_confirmation/confirm_and_submit. A few knowledge/checklist tools such as get_module_playbook, get_skill, and search_book could overlap at the margins, but their descriptions separate modules, workflow skills, and cited passages well enough.
The set overwhelmingly follows lower_snake_case action_object naming like get_*, list_*, prepare_*, fill_fields, and open_portal. Minor deviations such as confirm_and_submit and wait_for_user_ready are still imperative and readable, so the naming remains predictable overall.
At 25 tools, the server sits at the top of the 'heavy but borderline' range. The broad advisory/portal-automation scope mostly justifies the count, but several browser-session helpers and guidance/checklist tools could plausibly be consolidated without losing core capability.
The tool surface covers the full workflow: intake, risk assessment, guidance, module/skill selection, drafting and review bundles, self-serve or assisted browsing, form filling, and guarded submission. Minor gaps like updating intake data or checking post-submission status are workable rather than fatal.