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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the description's job is to add what they don't cover: it does, disclosing the result ceiling (up to five), the exact returned fields, the link-out behaviour, and the constraint that only published walks exist. It leaves out pagination behaviour and whether results are locale-filtered, but the behavioral picture is substantially richer than the annotations alone.

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?

Purpose and use-case triggers are front-loaded, and each subsequent sentence adds a distinct fact: return payload, coverage caveat. The return-payload sentence is long and list-like, but every element (distance, minutes, stops, teaser, coordinates, deep link) is decision-relevant, so little is wasted.

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 three-parameter read tool with no output schema, the description covers purpose, triggers, result shape, result ceiling and catalog scope — enough for correct invocation. The only meaningful hole is locale semantics, which is left entirely to the enum.

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?

With only 33% schema description coverage, the description should carry more weight; it does explain that results cap at five (clarifying the limit maximum) and restates the query meaning as a place rather than personal details. However, the locale parameter is never mentioned — an agent can see the enum values but not what they affect (UI language vs. audio language) — and the default limit of 3 is unaddressed.

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 ("Find self-guided Mappu walking tours") and narrows the target to a city, neighbourhood or landmark, which separates it from siblings like mappu_get_audio_guide and mappu_search_public_travel. An agent can tell what it retrieves without opening the schema.

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 concrete when-to-use triggers with quoted example requests ("a day in Lisbon", "what to see in Kyoto") and frames the output as an offer alongside a trip plan, which implicitly subordinates it to mappu_get_trip_planning_guide. It adds a scope boundary ("Covers only walks Mappu has published; a trip plan does not have to follow them") but never names the sibling tools an agent should switch to.

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