Publish a post now

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

The description goes beyond annotations by disclosing that it uses the 'real scheduler/provider pipeline', that records become PUBLISHED only after platform publishing succeeds (async, state transition), and that this 'can reach a LIVE AUDIENCE' (real-world side effect). It also explains permission behavior (draft-scoped token gets 403, human approval needed). This adds significant context beyond the basic readOnly=false, idempotent=false annotations, with no contradictions.

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?

Three concise sentences: first states the action and constraints, second explains the pipeline and state outcome, third warns about permissions and capability. Front-loaded with the primary verb and resource, every sentence adds unique value, no redundancy, within reasonable length.

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 simple action with one parameter and no output schema, the description covers purpose, usage constraints, behavioral effect, permission requirements, and state transition. It even mentions the real-world impact (live audience). No significant missing context; the absence of return value details is acceptable since this is a command-style action and the success/failure is inherent.

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 100% (id described as 'Post id'), so baseline is 3. The description adds eligibility semantics: the id must refer to an 'existing draft/scheduled/failed post' and 'must belong to the active org', which is not in the schema. It also implies the id type (string identifier) but reinforces that not all posts are valid targets. Valuable enrichment beyond schema.

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 clearly states the action: 'Queue an existing draft/scheduled/failed post for immediate publishing on the next scheduler tick'. It names the resource (post), the scope (existing draft/scheduled/failed, active org), and the timing (immediate/next tick), distinguishing it from siblings like schedule_post (future scheduling) and cancel_post. The CAPABILITY warning adds important context about live audience impact.

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 specifies when to use (for any existing draft/scheduled/failed post needing immediate publication) and provides a when-not/alternative: 'A draft-scoped token gets a 403 here; a human must approve at timetopost.co instead.' It implicitly contrasts with scheduling via 'immediate publishing' but does not explicitly name sibling tools like schedule_post or cancel_post. Slight gap in explicit alternative naming, but the guidance is clear.

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