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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior: the tool returns procedural instructions rather than search results, opens nothing itself, and the real work must be done by cotlet_browser_* tools. The added note that Resy has no public API explains why this instruction-returning design exists, though the return shape is only sketched as 'screens, buttons, 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, no filler, and the browser-tool handoff is stated plainly. However, the front-loaded sentence is the most misleading one, burying the tool's actual behavior mid-paragraph, and the trailing 'Resy's official API: Resy has no public API (checked 27 Oct 2026)' is awkwardly phrased provenance trivia that adds little for an agent.

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 output schema, the description carries the full burden of describing what comes back, and it only characterizes the result as step-by-step screens/buttons/fields. Combined with a zero-parameter schema, an agent still does not know how to express what to search for or how much guidance it will receive, which are the two things it needs before calling.

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?

The schema is an empty object with 100% coverage, so there are no parameters to disambiguate and the baseline applies. The description does not address the resulting oddity — with no query parameter, an agent is left guessing how the 'search' subject is conveyed (presumably in prose) — but with zero inputs there is little parameter meaning to add.

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 eventually reveals the real behavior — 'Returns how to do it in Resy step by step (screens, buttons, fields) and opens nothing by itself' — which is a specific and unusual purpose worth stating. But it leads with 'Search restaurants in the user's own Resy account,' the same wording as the title, so the first thing an agent reads suggests the tool performs a search rather than emits a guide. It also never distinguishes itself from resy_check_availability or resy_list_reservations, both of which an agent could plausibly reach for when looking for restaurants.

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?

It gives an explicit handoff: get the steps here, 'then do it with the cotlet_browser_* tools in the user's Resy Cloud Browser,' which names the alternatives and the sequence. What is missing is any exclusion — nothing tells the agent why it would pick this over check_availability, or whether this is mandatory before every Resy browser action.

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