wcway

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real behavioral content: a cap of 20 results, distance sorting, and the fields returned (walk time, fee, open now, closing time, wheelchair access, map link). Slight redundancy since an output schema exists, but this is genuine disclosure beyond structured 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?

Three sentences, front-loaded with the trigger, then the result shape, then the exclusion. No filler, and the negative guidance is short and high-value.

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 an output schema present and 90% parameter coverage, the description need not restate return fields, and the essential trigger/scope is covered. Missing only edge-case guidance (e.g., what happens with no location argument, or which of place vs lat/lon wins), which is minor at this complexity.

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 90%, so the schema already explains lat/lon, place, country and every filter flag; baseline 3 applies. The description adds only an implicit notion of place-based search and says nothing about parameter interactions (lat/lon vs place, how limit and the 20-cap relate).

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 gives a specific verb and resource plus scope: 'nearest public toilet' or 'toilets near a street, station or town.' It even guards against a semantic false positive ('toilet products or plumbing'). It does not, however, differentiate itself from the sibling get_toilet, which an agent must otherwise infer from the name alone.

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?

Trigger condition is stated explicitly ('Use this when the user asks for the nearest public toilet, or for toilets near a street, station or town') and paired with an explicit exclusion ('Do not use it for toilet products or plumbing'). Only gap is that it doesn't route to get_toilet for a single known toilet, but the when/when-not framing is unusually complete.

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?

Annotations already declare read-only, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new context by naming the fact categories returned and explaining that provenance encodes confirmation counts or source attribution, which is behavioral detail the annotations cannot carry.

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 front-loaded sentences: trigger first, prerequisite second, return semantics third. Efficient with almost no waste, though the provenance sentence could be trimmed slightly.

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 an output schema present the description need not detail return shapes, and it still adds the one non-obvious interpretive cue (provenance meaning). Nothing an agent needs to call it correctly is missing, though error behavior for a stale or invalid id is 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 100% and the single id parameter is already documented in the schema as 'Toilet id from find_toilets_near'. The description restates the same dependency without adding format, pattern, or fallback guidance, so 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?

States a specific verb and resource (get one toilet) and immediately scopes it to a single record retrieved from an earlier answer, which cleanly separates it from the plural sibling find_toilets_near. The enumerated fields (hours, access rule, fee, last confirmation) sharpen what 'one toilet' means.

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 an explicit trigger ('when the user asks about one toilet from an earlier answer') and names the upstream source of the required id ('the id from find_toilets_near'), routing the agent through the sibling rather than leaving the dependency implicit.

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