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

Beyond the annotations (readOnly, idempotent, non-destructive, closed-world), the description adds key behavioral context: it 'opens nothing by itself' and returns procedural instructions rather than data, and it discloses that Dext has no official API or MCP server. This is meaningful added value and consistent with readOnlyHint=true.

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?

Front-loads the core purpose and the 'does not open anything' caveat before the workflow guidance. The closing sentence on Dext's lack of an API is slightly verbose but earns its place by justifying why a guide-based tool exists.

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 zero-parameter, no-output-schema guide tool, the description covers what it returns (step-by-step instructions), what it does not do (opens nothing), and the follow-up path. Complete enough for an agent to call it correctly.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. No parameter-level detail is needed or missing.

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 resource (Dext costs) and, critically, clarifies that the tool does not actually export anything but returns step-by-step instructions (screens, buttons, fields). This resolves the tension with the action-oriented name 'Export costs'. It could be sharper about the deliverable (a guide, not data), but an agent can tell it apart from cotlet_browser_* which do the actual work.

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 explicitly names the next step and the alternative: use cotlet_browser_* tools in the user's Dext Cloud Browser to perform the export. It does not spell out when-not-to-use (e.g., if the user has API access), but that is implicitly moot because the description notes Dext has no public API.

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