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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds two genuinely useful facts beyond that: it is 'Free' (no credit charge) and starts 'no browser session.' It also previews the shape of the returned guidance, which matters since there is no output schema. This is solid added context but not deeply behavioral.

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?

The key instruction ('Call it before the first browser step in an app') is front-loaded as the penultimate sentence, and no sentence is pure filler. The first sentence is a long comma-heavy list, which is dense but still readable, so it stops short of a 5 on structure.

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 burden of telling the agent what comes back, and it does: browser/workspace choice, sign-in link, method, screens and actions, notes, and app-specific tools. It also notes the fallback for uncatalogued apps. Only minor gaps remain, such as whether the guidance is cached or per-workspace scoped.

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 coverage is 100%, including a documented default (ShootProof) for 'app' and a definition for 'task' ('in their words'). The description echoes app/task relevance through phrases like 'the app's dedicated tools' and 'what the user wants done,' but adds no syntax, format, or matching guidance beyond the schema. Baseline 3 is appropriate.

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 states a specific purpose: retrieving guidance for driving a web app through Cotlet's browser tools, and enumerates what the guidance contains (browser choice, sign-in link, step-by-step method, screens/menus/actions, dedicated tools). It is distinguishable from the cotlet_browser_* siblings because it is a preparatory knowledge lookup rather than an actual browser action. It is slightly abstract and verbose, but an agent can tell what it gets back.

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?

Explicit timing guidance is given: 'Call it before the first browser step in an app.' It also clarifies coverage scope ('Works for any web app; one outside Cotlet's catalog gets the general method'), which tells the agent not to skip it for unknown apps. It lacks an explicit when-not-to-call clause, so it falls short of a 5.

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