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

Annotations already declare readOnly/idempotent/non-destructive, but 'Free, no browser session' adds cost and resource context an agent cannot infer from the hints — meaningful for deciding whether to call it up front. It also enumerates what comes back (sign-in link, method, screens, notes), which matters since no output schema exists. It does not say how long or structured that guidance is, or whether a 120-char app slug miss falls back silently.

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 what you get and immediately followed by the triggering condition. The middle sentence is a long comma-separated inventory that is slightly hard to parse on one read, but no sentence is filler.

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 two-optional-parameter guidance tool with no output schema, the description covers when to call, what it returns, and that uncataloged apps still get a general method. Remaining gap: nothing about repeat calls per step versus once per app, and 'this workspace' is referenced although no workspace parameter exists.

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% — both `app` (name or Cotlet slug, default Copper CRM) and `task` (user's own words) are documented in the schema. The description only implies that the app determines the route and sign-in link, and never explains how `task` shapes the returned method. Baseline 3 applies when the schema carries the semantics.

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 makes clear this is a guidance-retrieval tool: it returns the browser to use, the sign-in link, a step-by-step method, the app's screens/menus/actions, and any app-specific tools. That distinguishes it from the cotlet_browser_* action siblings. The opening phrase 'How to work in an app by clicking...' is noun-heavy and reads as an instruction rather than 'returns a playbook for', which slightly blunts the verb/resource pairing.

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?

'Call it before the first browser step in an app' is an explicit, actionable trigger tied to the sibling tool family. 'Works for any web app; one outside Cotlet's catalog gets the general method' scopes coverage for uncataloged apps. No explicit when-not or a named sibling to prefer instead (e.g., cotlet_apps for listing), so it stops short of full routing guidance.

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