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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety bar is low. The description still adds meaningful context beyond them: it explicitly says it 'opens nothing by itself' and specifies the return payload shape (screens, buttons, fields), which is exactly the behavioral detail annotations cannot convey. It stops short of saying whether the instructions are account-specific or generic, which would have made it a 5.

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 core operational content is squeezed into one long sentence, while front-loading is spent on filler ('from ChatGPT, Claude or any AI agent') that adds nothing for an agent. The trailing paragraph about Tumblr's public API v2 and the absence of an official MCP server (with a checked date) is background justification, not invocation guidance, and consumes roughly a third of the text. A tighter version would lead with the return contract and the browser handoff.

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, non-destructive read tool with no output schema and full annotation coverage, the description supplies the two things an agent actually needs: what comes back (step-by-step screens/buttons/fields) and what to do next (cotlet_browser_* tools). The absence of an output schema means the return shape had to be described in prose, and it is. Only the generic-vs-account-specific nature of the instructions is left 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 tool takes zero parameters, so there are no parameter semantics for the description to explain and the baseline of 4 applies. The description correctly implies a no-argument call by describing the tool as self-contained and side-effect-free.

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 does state a concrete behavior: it 'Returns how to do it in Tumblr step by step (screens, buttons, fields) and opens nothing by itself,' which tells an agent this is an instruction-returning tool rather than a live data fetch. However, the lead sentence 'List queue in the user's own Tumblr account' and the matching title suggest the tool returns queue contents, creating a real risk that an agent calls it expecting data. The actual verb+resource (return a how-to guide for the queue screen) is buried in the second sentence, so the purpose is recoverable but not front-loaded.

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?

The description does give a two-step workflow: call this, then act with the cotlet_browser_* tools in the user's Tumblr Cloud Browser, which is genuine usage guidance. It does not say when NOT to use it, nor does it point to any specific named sibling (e.g. cotlet_app_guide or cotlet_apps) as an alternative for other Tumblr tasks, leaving the agent to infer routing from sibling names alone. The guidance is implied and partial rather than explicit.

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