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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so 'opens nothing by itself' mostly restates them. The genuinely additive context is the note that no documented EZ Lawn Biller API exists, which tells the agent not to hunt for an API path and to route execution through the browser tools.

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 purpose and the follow-up action are front-loaded in the first sentence, which is the right structure. The closing note on 404s at ezlawnbiller.com/api, /developers and /docs is lengthy and dated but earns its place by closing off a plausible wrong approach.

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, read-only assistance tool with no output schema, the description covers what comes back (step-by-step screens, buttons, fields) and what to do next. Only the boundary against the sibling manual_help tool is left unaddressed.

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; a 4 baseline applies. The description's focus is properly on what the call returns rather than on inputs.

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?

States a specific verb and output ('Returns how to do it in EZ Lawn Biller step by step (screens, buttons, fields)') for the estimate domain. It does not, however, distinguish itself from the sibling ez_lawn_biller_manual_help, so an agent must guess which help tool covers which scope.

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 a workflow cue — get steps here, then execute with the cotlet_browser_* tools — and warns it 'opens nothing by itself'. It offers no explicit when-not guidance or comparison to the manual_help sibling, so the choice between help tools is implied rather than stated.

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