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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds value beyond that: it is a full-text web-page search (open-web content, not structured GTFS), it carries an unofficial/not-affiliated disclaimer, and it imposes a no-memory-of-facts grounding constraint. It does not describe result richness or coverage limits, which keeps it below 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?

Front-loaded with the capability line, then the exclusion/alternative routing, then a compact Args block, then the grounding rule. Every sentence carries distinct information — scope, exclusions, parameter values, or an anti-hallucination constraint — with no repetition of the title or annotations.

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?

An output schema exists, so return values need not be explained, and annotations cover the safety/idempotency profile. What remains for a search tool — content scope, exclusions, all three parameter semantics including the undocumented enum, and grounding expectations — is fully covered.

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 0% and the category parameter has no enum in the schema (plain anyOf string/null), so the description carries the full burden — and it does: it enumerates all 13 allowed category values, gives natural-language query examples ('pay with phone', 'bringing a bike'), and states the limit default. Minor gaps remain: no maximum for limit and no statement of how category matching works.

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 verb+resource ('full-text search of the agencies' web pages') and immediately scopes the covered content (fares, payment, accessibility, safety, rules, guides, service changes). It then explicitly disclaims what it does NOT cover and names the sibling tools (get_metro_route, plan_connection, get_route, transfers_at) that handle routes/stops/schedules, so an agent can distinguish it from siblings without opening any 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 both the when (rider-page questions: fares, payment, accessibility, visitor guides) and the when-not (routes, stops, schedules, hours, service days), with named alternative tools for each excluded case. It also adds a grounding rule — answer only from this tool's results, never from memory — which is actionable usage guidance an agent would otherwise lack.

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