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

Goes well beyond the annotations (which only declare non-readonly, open-world, non-idempotent, non-destructive) by disclosing character limits per platform, the sentence-boundary truncation behavior with adjustedPlatforms and warnings in the response, the all-or-nothing rule for explicit platformVersions, and Substack profile-routing safety that can return action_required without publishing. These are non-obvious side effects an agent must anticipate.

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 in the first sentence and the remainder is information-dense rather than padded. Some sentences are long and pack multiple constraints (character limits plus truncation plus routing rules) that would read better as a short list, but there is little actual waste.

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 20-parameter, nested-object tool with an output schema, the description covers the high-risk behaviors (draft-vs-draftId path, platform limits, truncation reporting, Substack identity failures) that the schema alone would not convey. It leaves media attachment and Instagram destination handling entirely to the schema, which is a minor remaining gap.

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?

Schema coverage is already 95%, so the baseline is 3, but the description adds genuine meaning: platform-specific limits tied to platformVersions, team routing via workspace/writer, and the Substack publication/profile requirement. It does not cover media, imageUrls/videoUrls, or instagramDestinations, so it is not exhaustive.

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 resource ('Schedule a note') plus the exact set of target platforms, so the agent knows precisely what the tool does. It distinguishes implicitly from the sibling 'schedule_article' by using 'note', but never names or contrasts siblings explicitly, keeping it below a 5.

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 useful conditional context — 'Creates a note draft when draftId is absent' and 'Authorized team routing uses workspace and writer' — which helps the agent pick the right call shape. However, it never states when to prefer this tool over siblings like schedule_article or create_draft, nor any explicit exclusions.

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