UK Places MCP

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

With no annotations, the description carries the full load and does well: it names the geocoding dependency (postcodes.io), the 24h cache, the data license (© OpenStreetMap contributors / ODbL), and that outbound soft-offers are disabled. It omits failure behavior for invalid or non-UK postcodes and does not say whether results include distance or category fields.

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?

Four short clauses, front-loaded with the scope ('Free peek: up to 5 …'), then supporting facts about geocoding, caching, licensing and the disabled upsell. Nothing is padded; every fragment carries distinct information.

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 read with no output schema, the description still leaves the return shape unspecified — an agent does not know which amenity fields come back (name, type, distance) or how errors surface for a malformed postcode. Adequate but with a real gap given the absence of an output schema.

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 parameters are already documented. The description only restates the postcode format and the 5-result cap, adding no new semantics such as what 'size' below 5 does or whether outcode results differ from full postcode results. 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 concrete resource and scope: nearby OSM amenities for a UK postcode/outcode, capped at 5 for the free tier. The 'Free peek' framing hints at the paid sibling local_amenities_pack, but it never names it, so an agent must infer the tier relationship.

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 word 'Free peek' plus 'max 5 for free' implies this is the trial-tier lookup and that a fuller pack exists, but no explicit when-to-use or when-to-switch guidance is given relative to local_amenities_pack or local_context_pack. Usage is implied rather than stated.

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 that the call is billable (£0.49), that it returns a Stripe Checkout URL rather than amenity data, that the data is OSM/ODbL with attribution obligations, and that 'Soft-Offer outbound is OFF'. It omits auth requirements, rate limits, and what the caller should do after payment completes.

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 the purpose and cost, no filler. 'Soft-Offer outbound is OFF' is unexplained internal jargon, which costs it a point, but everything else 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?

No output schema exists, and the description compensates by naming the exact return artifact (Stripe Checkout URL), which is the single most important thing an agent needs to know. The remaining gap is the workflow tail — nothing points to redeem_pack as the follow-up after payment.

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 parameters (postcode, size) are already documented, and the baseline is 3. The description reinforces the postcode/outcode input format but adds nothing about the 'size' parameter's default or max.

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 ('pack of nearby UK amenities') with a concrete scope ('for a postcode/outcode') and adds the material fact that it is a paid pack. It does not explicitly name or contrast with the sibling local_amenities_discover, so the free-vs-paid distinction must be inferred from the word 'Paid'.

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 explicit when-to-use statement or exclusion; the only guidance is implicit via 'Paid' and the £0.49 price, which hints this is the purchase path rather than the discovery path. Nothing tells the agent to prefer local_amenities_discover when a free lookup suffices.

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 must carry the behavioral burden, and it does disclose two important traits: it is a paid operation (£0.49) and it returns a Stripe Checkout URL rather than the data itself. However, it never explains the post-payment flow, whether/when the pack becomes retrievable (presumably via redeem_pack), or whether calling it charges the user immediately.

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 the payload contents front-loaded, which is good, but 'honest risk_flags' is promotional filler and 'Soft-Offer outbound is OFF' is unexplained internal jargon that consumes space without conveying actionable meaning.

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 paid, multi-part tool with no annotations and no output schema, the description omits the most consequential facts an agent needs: what a call actually returns (only a checkout URL? the pack?), how the pack is later retrieved relative to redeem_pack, and whether repeat calls incur repeat charges.

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 'size' (default 25, max 100) and 'postcode' (UK postcode or outward code) are already fully documented in the schema. The description adds nothing about parameter behavior, 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?

Names the resource precisely and enumerates its contents (OSM amenities + density stats + risk_flags), plus the payment/return aspect. The word 'compound' hints at bundling multiple data types unlike the sibling local_amenities_pack, but the description never explicitly contrasts with siblings, so the differentiation is inferred rather than stated.

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?

No when-to-use clause, no prerequisites, and no reference to the obvious alternatives (local_amenities_discover, local_amenities_pack, redeem_pack) among which an agent must choose. 'Soft-Offer outbound is OFF' is opaque jargon that provides no actionable selection 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?

With no annotations, the description carries the full behavioral burden. It implies a state-changing redemption but says nothing about idempotency, what happens if the session was already redeemed or is unpaid, whether authentication/ownership of the session is required, or what the call produces (a pack entitlement? credits?). Those are exactly the facts an agent needs before invoking a mutation.

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, no filler, with the action stated first and the parameter hint second. The only structural weakness is that the leading phrase "Instructions to redeem" reads like a doc pointer rather than a description of the operation.

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?

The tool is simple (one required param, no output schema), but for a redemption flow the missing outcome information matters: what the agent gets back, whether the pack becomes usable by the sibling pack tools, and what failure modes exist. With no annotations and no output schema to fall back on, the description leaves an agent guessing at the result of a write operation.

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 schema already documents session_id as a Stripe Checkout id in cs_... form. The description adds only that the value comes "from checkout", a marginal sourcing hint beyond the schema. Baseline 3 is appropriate.

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 Stripe Checkout session) but the framing "Instructions to redeem..." is ambiguous about whether the tool performs the redemption or merely returns instructions for doing so. It also gives no hint of how this relates to the sibling 'pack' tools (tenders_pack, tender_score_pack), which an agent would reasonably wonder about given the shared naming.

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?

"Pass session_id from checkout" is the only usage cue and it addresses argument sourcing, not when to call the tool. There is no guidance on preconditions (session must be paid, not already redeemed) or on when an agent should prefer or avoid this tool relative to its siblings.

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