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

Annotations already establish this is a safe, idempotent, non-destructive read. The description adds real behavior beyond them: 'Free, no browser session' tells the agent this call costs nothing and does not consume or alter the user's Cloud Browser state, which matters when sequencing before browser steps. It does not describe return shape or size, but no output schema exists to conflict with.

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 content is dense and front-loaded: the purpose and the enumerated output are stated before the call-timing rule. It reads as one long comma-chained sentence that sprawls a bit through the list of contents, but there is almost no filler and every clause contributes information.

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 simple, no-required-parameter read tool with full schema coverage, safe annotations, and no output schema, the description covers what it returns, when to call it, and its cost profile. The only residual gap is guidance on repeated calls per app and its relationship to cotlet_apps.

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%, so both 'app' and 'task' are already documented in the schema, including the Fiken default. The description only obliquely touches the 'app' parameter ('one outside Cotlet's catalog gets the general method') and says nothing about what 'task' does to the output, so it adds little beyond the structured fields.

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 uses a specific verb and resource ('how to work in an app ... with Cotlet's browser tools') and enumerates the payload in concrete terms: which browser to use, the sign-in link, the step-by-step method, screens/menus/actions, notes, and dedicated tools. This clearly separates it from the cotlet_browser_* action tools, but it never distinguishes itself from cotlet_apps, which a reader could easily confuse it with.

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' gives a precise trigger point relative to the browser siblings, and 'Works for any web app; one outside Cotlet's catalog gets the general method' scopes the expected coverage. There is no explicit when-not guidance, however, such as whether it is worth calling repeatedly for the same app or how it relates to cotlet_apps.

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