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

Goes well beyond the annotations, which only declare the write/destructive/open-world/idempotent profile. The description discloses the unconfirmed-send failure mode, warns against creating a replacement to retry, explains the expectedUpdatedAt concurrency guard, and gives an app-only recovery path (Activity > check status > confirm no post) — exactly the behavioral context annotations cannot carry.

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?

Tight, front-loaded prose where each clause carries operational meaning (precondition, concurrency, retry warning, recovery). The final recovery sentence is dense but earns its place; nothing is padded.

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?

With an output schema present, return values need not be described, and the description covers precondition, concurrency, retry, and recovery. The only real gap is the unexplained substackConnectionId parameter.

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 0%, so the description must carry the parameter burden. It explains expectedUpdatedAt well ('supply updatedAt as expectedUpdatedAt'), but leaves draftId and substackConnectionId undefined, so it only partially compensates for the coverage gap.

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: 'Publish one saved reply', which clearly distinguishes this terminal publish action from create_reader_reply_draft, update_reader_reply_draft, and list_reader_reply_drafts. It does not explicitly name those siblings, so an agent must infer the boundary, but the purpose itself is unambiguous.

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 a concrete precondition: use only after the user has reviewed and approved the full text and target comment. This is strong context but stops short of naming the alternative action (e.g., update the draft first) that an agent should take when approval is absent.

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