UK Companies House MCP

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

With no annotations, the description carries the full behavioral burden, and it does disclose several important traits: the operation is paid (£0.49), it returns a Stripe Checkout URL rather than the data itself, and the indicators are explicitly not a due-diligence/KYB opinion. These are meaningful disclosures an agent needs. However, it omits auth requirements, whether the company number is validated, and what the agent should do after receiving the checkout URL (e.g., redeem_pack), leaving real gaps.

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 purpose and pack contents are front-loaded, and the parenthetical enumeration is efficient shorthand. The trailing 'Soft-Offer outbound is OFF' is cryptic and arguably earns less of its place, but overall the text is compact and skimmable.

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 two-parameter tool with no output schema, the description covers cost, return shape (checkout URL), and the legal disclaimer, which is reasonably complete. It nonetheless leaves an agent unsure what to do with the checkout URL or how this relates to the redeem_pack sibling, so it is adequate rather than complete.

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%, with both company_number and filing_limit fully documented in the schema, so the baseline is 3. The description adds the 'one UK company number' scope but nothing about the filing_limit semantics or format beyond what the schema already states.

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 names a specific resource (a paid data pack for one UK company number) and enumerates exactly what the pack contains: profile, officers, PSC, filings, indicators. That is far more specific than a tautology. It does not explicitly differentiate itself from new_cos_pack or redeem_pack, but the 'one UK company number' scoping and enumerated contents give an agent a clear picture of what this tool produces.

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 statement of when to use this tool versus the siblings new_cos_discover, new_cos_pack, or redeem_pack, nor any prerequisites such as account/auth state. 'Soft-Offer outbound is OFF' hints at a policy context but does not tell the agent when this tool is appropriate. Usage must be inferred entirely from the name and pack contents.

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 and does real work: it discloses the paid nature (£0.49), the exact return artifact (a Stripe Checkout URL rather than the data itself), the mandatory follow-up redemption step, and a compliance posture ('Soft-Offer outbound is OFF'). It omits auth requirements, token expiry, and what happens if the purchase is abandoned.

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 short sentences, front-loaded with what the tool produces and followed by the required next step. The final clause about Soft-Offer outbound is terse and slightly cryptic, but every sentence carries information and nothing is padded.

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 two-parameter purchase tool with no annotations and no output schema, the description covers the essentials: cost, return value (Checkout URL), and the redemption handoff. It does not explain what the delivered pack actually contains or how the one-time token is obtained, leaving a modest gap.

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 both 'area' and 'size' are already documented in the schema, including the default of 25 and max of 100. The description only reinforces that the pack matches 'an area', adding no format or syntax detail beyond the schema — 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?

The description names a concrete resource ('paid pack of newly incorporated UK companies') and its scoping ('matching an area'), which distinguishes it from new_cos_discover and kyb_pack on subject matter. It does not name those siblings explicitly, so an agent must infer the routing rather than being told it.

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 is implied through the workflow: buy the pack, then 'redeem with one-time token', which points at the sibling redeem_pack without naming it. There is no explicit statement of when to choose this over new_cos_discover (free discovery) or kyb_pack, and no prerequisites such as account or payment-method requirements.

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. 'Redeem' implies a state-changing operation, but the description never says whether it is idempotent, what it grants, what happens if the session was already redeemed or is unpaid, or whether authentication is required. For a mutation-type tool with zero annotation coverage this is a real 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?

Two short sentences with no filler, and the action/purpose is front-loaded before the parameter instruction. It could be tightened ('Instructions to' adds no information) but it wastes very little space.

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?

There is no output schema and no annotations, so the description must carry behavioral and return context — but it says nothing about what redemption returns (entitlement, license, confirmation), idempotency, or failure modes. For a one-param mutation tool this leaves the agent guessing about the post-call state.

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 single parameter is fully documented in the schema ('Stripe Checkout session id (cs_...)'). The description adds only the origin hint 'from checkout', which is marginal value over the schema's own type/format description. Baseline 3 applies when the schema does the heavy lifting.

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 action (redeem) on a specific resource (a paid Stripe Checkout session) and even gives the trigger context '(success redirect)'. The 'Instructions to' phrasing is slightly awkward — it's unclear whether the tool performs the redemption or merely returns guidance — but the intent is largely readable. No sibling differentiation is possible since the sibling names (kyb_pack, new_cos_*) share no obvious surface.

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?

'(success redirect)' and 'Pass session_id from checkout' imply the calling context: invoke after a successful Stripe Checkout redirect, sourcing the id from that flow. This is implied rather than explicit — no statement of when NOT to call, whether it can be called twice for the same session, or what to do on failure.

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