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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile needs no restating. The description adds genuinely useful behavior not present in the structured fields: it consumes no browser session and costs nothing, and it returns method, screens, menus, actions, and notes rather than performing any browsing. It stops short of saying how the guide is scoped (per user? per workspace?) or how large the response can be.

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 with no filler, and the trigger condition is placed at the end where it is easy to find. The first sentence is a long colon-delimited list that is dense but still scannable; a tighter enumeration would improve it marginally.

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 read-only, zero-required-parameter guidance tool with no output schema, the description covers what the tool is, when to call it, and what it returns. The only meaningful gap is the fallback behavior detail for unknown apps and workspace scoping, which is minor given the simple schema and existing annotations.

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% and both parameters (app name/slug, task in the user's words) are already documented in the schema. The description adds only an implicit point: unrecognized apps fall back to a general method, which mildly informs how to populate 'app'. No examples of slug format or task phrasing are supplied, so the baseline of 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?

The description names the resource (an in-app working guide for the user's Cloud Browser) and enumerates its contents: which browser/sign-in link, step-by-step method, screens/menus/actions, notes, and dedicated tools. It is distinguishable from the cotlet_browser_* siblings through the phrase 'Free, no browser session,' though the opening clause is convoluted and the tool name itself carries much of the load.

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: 'Call it before the first browser step in an app,' which tells the agent exactly where this fits in a workflow, plus a coverage caveat that apps outside the catalog still get the general method. It does not mention any alternatives (e.g., using cotlet_apps to discover an app before asking for its guide), so the exclusions are implicit rather than stated.

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