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

Annotations declare readOnlyHint=true and destructiveHint=false, and the description reinforces rather than contradicts this by stating it 'opens nothing by itself'. It adds genuinely useful behavioral context the annotations do not carry: the return is procedural guidance (screens, buttons, fields) and the actual mutation happens via browser tools. It omits prerequisites such as whether a connected Gymdesk Cloud Browser session is required first.

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?

Purpose is front-loaded, but the first sentence is a run-on that mixes product names with the action and delays the key clarification. The closing note about 404s at gymdesk.com/api, gymdesk.com/developers and docs.gymdesk.com/api on 11 Nov 2026 is low-value evidence for the agent and could be compressed to one clause justifying the manual route.

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 describing the return value, and it does so at a high level (step-by-step instructions with screens, buttons, fields) while clarifying no action is taken. Since it is a zero-parameter, read-only guidance tool, little else is strictly needed, though the response format and any session prerequisites remain unstated.

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 schema is an empty object with no parameters, so there is nothing for the description to disambiguate. Baseline for zero-parameter tools applies, and no misleading parameter hints are introduced.

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 second sentence is specific: it returns step-by-step Gymdesk instructions (screens, buttons, fields) and explicitly does not perform the action itself. The opening phrase 'Add a lead manually... from ChatGPT, Claude or any AI agent' initially reads like an execution tool, which creates a brief ambiguity that the next sentence resolves. It distinguishes itself from the cotlet_browser_* tools but does not differentiate from sibling Gymdesk lead tools such as gymdesk_add_or_quick_add_a_member_or_visitor.

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 clearly states the workflow: use this to get instructions, then execute with cotlet_browser_* tools in the Cloud Browser. That is a usable when-to-use plus a named alternative. It stops short of exclusions — it never says when not to use it versus other lead-creation or lead-management siblings.

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