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. The description reinforces this with 'opens nothing by itself', which is the single most important behavioral fact for an agent that might otherwise fear a real send. It also discloses the nature of the return payload (screens, buttons, fields) and the API limitation, though it gives no guidance on what happens if the walked-through action fails.

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 clarification ('returns how to do it... opens nothing by itself') is front-loaded, which is good. But the opening clause 'Send direct message in the user's own Substack account from ChatGPT, Claude or any AI agent' restates the misleading name and adds marketing framing, and the trailing 'Substack's official API: Substack has only a limited API (checked 11 Oct 2026)' is a stale timestamped aside that does not change how the agent calls the tool.

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 tool with no output schema, the description does explain what comes back and that no side effect occurs, which covers the essentials. However it never clarifies its relationship to the near-identically named `send_message`, leaving the biggest routing ambiguity unresolved for an agent choosing among ~70 siblings.

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. The schema's additionalProperties:false and empty properties are fully consistent with the description's picture of a parameterless guide call.

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 corrects a misleading name by stating the tool 'Returns how to do it in Substack step by step (screens, buttons, fields) and opens nothing by itself' — so it is a guide generator, not a sender. That is specific verb+resource information an agent could not infer from the title. It stops short of naming the sibling `send_message`, which is the tool that actually performs the action, so sibling differentiation is only partial.

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 implies the workflow by saying 'then do it with the cotlet_browser_* tools in the user's Substack Cloud Browser', which tells the agent what to do after calling this. But it never states when to pick this over `send_message` or `cotlet_app_guide`, and gives no explicit exclusion. Usage is inferable rather than stated.

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