propose_reply

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

No annotations are provided, so the description carries full burden. It discloses that the tool performs a write (but no Substack call yet), computes a dedup hash, builds the exact payload, stores it under a token, and returns token+preview. It mentions token expiration. It doesn't cover authentication or rate limits, but overall provides good behavioral context.

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 description is four sentences, front-loaded with the core action ('STAGE A WRITE'). Every sentence adds value: validation, hashing, payload building, token storage, preview, approval flow, token expiry, and parameter guidance. No wasted words.

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?

Given no annotations, no output schema, and 6 parameters, the description covers the essential lifecycle (propose then confirm), parameter rules, and token expiration. It doesn't describe return format or error handling, but those are less critical for this two-phase workflow. It is sufficiently complete for the complexity.

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 input schema has 0% description coverage, so the description must add meaning. It explains that 'kind' determines which IDs are required: 'post' needs post_id and parent_comment_id, 'note' needs note_id. It also clarifies that body is required. It does not explain 'pub' or default values, but the key parameters are well explained.

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 states the tool stages a write (validate, compute dedup hash, build payload, store under token) and returns token+preview. It distinguishes from siblings by explicitly noting that new top-level comments should use 'comment_on_post' and that approval requires 'confirm_reply' with the same token. This is a specific verb+resource with clear sibling differentiation.

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 explicitly tells when to use this tool (staging a reply before approval) and when not (for new top-level posts, use comment_on_post). It provides parameter requirements per kind: 'post' requires post_id + parent_comment_id, 'note' requires note_id. It also instructs to call confirm_reply on approval and notes token expiry in 5 minutes.

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