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

Annotations already declare readOnly/non-destructive/idempotent; the description adds the key behavior they don't convey — that it opens nothing and only returns textual guidance, and that execution happens via a separate browser tool set. That is the single most important thing an agent needs to know here. No mention of what the returned guidance contains beyond 'screens, buttons, fields'.

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 actionable content (returns instructions, use browser tools) is front-loaded and good. But 'from ChatGPT, Claude or any AI agent' and the closing 'Strava's official API... official MCP connector (checked 27 Oct 2026)' are marketing filler that adds no calling guidance and dilutes focus.

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 tool the description covers the essential handoff and return shape reasonably. However, it never explains how the agent knows which activity to act on without an identifier parameter, and the trailing API/connector sentence raises questions rather than resolving them.

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?

Zero parameters, so there is nothing for the schema to document and no parameter semantics to compensate for. Baseline 4 applies. Notably, the absence of any activity identifier parameter is a real gap an agent would notice, but the description is not the place that schema lives.

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 makes clear the tool returns step-by-step Strava UI instructions rather than posting a comment itself ('Returns how to do it in Strava step by step... opens nothing by itself'). This is a specific and non-obvious purpose. It loses a point because the name 'strava_comment_on_activity' sets up the opposite expectation and has to be corrected mid-description.

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 names the follow-on tool family explicitly ('then do it with the cotlet_browser_* tools in the user's Strava Cloud Browser'), which tells the agent this is a first step in a two-part workflow. It doesn't say when NOT to use it or how it relates to strava_list_activities or cotlet_app_guide.

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