UK Visa Sponsor Register MCP

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. It implies a read/list operation and explains the B-rated status, but does not state auth requirements beyond the schema, return format, pagination, rate limits, or whether the operation has side effects. The domain context is useful but operational transparency is limited.

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 a single, front-loaded sentence with no wasted words, covering status meaning, optional filter, and intended signal. The leading 'PRO.' is slightly ambiguous and could be clearer, but overall structure is efficient.

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 no annotations and no output schema, the description should provide more operational context. It covers purpose and the optional town filter, but omits return shape, auth expectations, and any behavioral details an agent would need beyond the partial schema. For a query tool with an undocumented town parameter, this is 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 50%: access_token is documented in the schema, while town is not. The description adds meaning for town by saying it is optional and acts as a filter, which partially compensates for the schema gap, but it does not specify town format (name, code, etc.). The access_token parameter is covered by the schema and needs no further elaboration.

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 clearly identifies the resource and filter: sponsors currently B-rated, with optional town filtering. It also clarifies what B-rated means in this domain (downgraded, on an action plan). It does not explicitly differentiate itself from sibling tools such as sponsor_search, but the status-specific scope is distinct enough for an agent to understand its purpose.

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 phrase 'compliance risk signal' hints at a use case, and 'optionally by town' indicates a filtering option. However, there is no explicit guidance on when to use this tool versus siblings like sponsor_search or sponsor_check, nor any exclusions or prerequisites. An agent must infer usage 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?

With no annotations, the description carries the full burden. It usefully discloses the 'PRO' paid-tier gating and clarifies that 'removed' means possible revocation or surrender, which is real semantic value. However it says nothing about return format, pagination, or what happens with an absent access_token.

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 compact sentences, front-loaded with the tier marker and the core delta definition. The parenthetical clarification earns its place; 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 simple one-parameter read tool with no output schema and no annotations, the description covers what the tool is and the tier requirement. Gaps remain around result shape, ordering, and volume, which an agent would want given there is no output schema to fall back on.

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?

Single parameter with 100% schema description coverage, so the schema already explains access_token sourcing. The description adds nothing about the token, but it also doesn't need to — 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?

Names a specific resource (sponsor register) and a specific delta scope (organisations added or removed since the previous daily update), plus a useful gloss on 'removed'. It does not differentiate itself from siblings like sponsor_search or register_stats, and the name alone would be ambiguous without the description.

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 phrase 'since the previous daily update' implies a monitoring/change-tracking use case, but there is no explicit when-to-use, no when-not-to-use, and no pointer to sponsor_search or register_stats for other needs. The agent must infer the routing decision entirely.

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. It discloses the 'top 30' truncation, which is useful, but does not explain the 'PRO.' gating requirement, what auth is needed, or what the result shape looks like for a subscription-gated stats call.

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 clauses with no waste and the aggregation scope front-loaded. The cryptic 'PRO.' token is the only piece that costs the reader without paying back in clarity.

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 one-parameter stats tool with full schema coverage and no output schema, the description covers the aggregation and its cap. It falls short on access gating and usage context, which an agent needs to invoke it correctly.

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?

There is a single parameter with 100% schema description coverage, so the schema already documents access_token. The description adds nothing about authentication semantics beyond the bare 'PRO.' hint. 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 resource and aggregation: sponsor counts grouped by route and by town, limited to top 30. An agent can tell this is an aggregate stats tool, though the name 'register_stats' doesn't align with 'sponsors' and no sibling (sponsor_search, sponsor_check) is named as the non-aggregate alternative.

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 only contextual cue is the 'PRO.' prefix, which implies a subscription gate but never explains it. There is no guidance on when to use this versus sponsor_search or b_rated, nor on choosing between route and town grouping.

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 well: it discloses cost (FREE), data freshness (today's Home Office register), return contents (rating A/B and routes) and result truncation (top 3 matches). It omits what happens on zero matches or whether matching is exact or fuzzy, keeping it short of a 5.

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 tight sentences with the cost signal and the core question front-loaded; every clause carries information. The em-dash tail is slightly compressed but not wasteful.

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 one-parameter tool with no output schema it covers the essentials: what it returns, how many results, and how fresh the data is. The only real gap is no-match and matching-semantics behavior, which would matter to an agent deciding whether to retry.

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%, so the description must compensate for the single 'organisation' parameter. It implies the value is an organisation name and that matching is loose ('top 3 matches'), but adds no format guidance such as trading name vs registered name.

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 question the tool answers (is this organisation a licensed UK visa sponsor) plus the output shape (rating A/B, routes). It does not explicitly distinguish itself from the sibling sponsor_search, so an agent must infer the difference.

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 leading 'FREE' signals a cost preference and 'top 3 matches' implies fuzzy lookup, giving implied usage context. However, it never says when to use this versus sponsor_search or b_rated, and offers no exclusions.

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 supplied, so the description carries the full behavioral burden, yet 'PRO.' is unexplained — it likely signals a paid/subscriber gate but that is never stated. Nothing is said about the access_token requirement, how many results are returned, how the 'limit' behaves, or pagination, all of which matter for a list endpoint with no 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?

A single, front-loaded sentence that packs scope, the optional filter, and the audience with no filler. The only waste is the cryptic 'PRO.' prefix, which occupies prime position but conveys little.

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 four parameters, no annotations, no output schema, and only 25% schema coverage, the description should do more: it leaves the limit semantics, the authentication requirement implied by access_token, and the shape of results entirely unaddressed.

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 25%: only access_token is documented in the schema. The description compensates partially by clarifying that 'town' is a town/city and giving concrete route examples (Skilled Worker, Health and Care), but 'limit' is left completely uninterpreted and the required token gate is not restated.

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 verb (search/list) and resource (all licensed sponsors) with an explicit scope: a town/city, optionally narrowed by route. That is clear enough to act on, but it never distinguishes this from the sibling sponsor_check, so an agent must infer the boundary between 'list sponsors in an area' and 'check a sponsor'.

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 phrase 'lead lists for recruiters and immigration advisers' implies the intended use case, and 'optionally filtered by route' signals an optional narrowing. There is no explicit when-not condition and no named alternative among the siblings, so routing depends on inference.

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