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

Annotations only declare the generic write/openWorld/idempotent=false profile; the description goes well beyond by explaining conditional refusal states, the immediate-vs-scheduled publish behavior, and the safety rationale that only the person can verify the platform. This is 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?

Front-loaded with the primary action and eligibility, and every clause carries distinct information (states, timing, refusals). Slightly dense with parenthetical state references, but nothing is padding.

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?

An output schema exists, so return values need no explanation, and the description fully covers the prerequisites, refusal conditions, and timing semantics an agent needs to invoke this correctly. Complete for a single-parameter state-transition tool.

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 description coverage is 0% for the single target_id parameter, so the description must compensate; it implies target_id identifies a post target/approval subject but gives no format, source, or how to obtain the ID. It adds some meaning but not enough to fully cover the 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?

Names a specific verb (retry/publish again) and a specific resource (a target of an approved post that failed), and states the exact eligibility condition by referencing the retry: 'not posted' state from get_post. An agent can distinguish this from create_post, update_post, or mark_posted without opening any schema.

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?

Explicitly enumerates when to use it (target is 'not posted' or awaiting automatic retry), when it is refused ('unknown' retry state, unapproved posts), and routes the agent to alternatives (mark_posted for a live post, manual retry from the app). Nothing about the decision is left to inference.

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