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

Beyond the annotations, the description explains the state transition (back to pending), reversibility (a person can approve it again later), and the write-tier approval workflow (first use may require manager approval, from-now-on vs just-once approval, and not to re-ask). This adds meaningful behavioral context without contradicting destructiveHint or readOnlyHint.

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 front-loaded with the core purpose, then flows into usage routing and the approval note. Each paragraph earns its place; the routing and write-tier details are essential and not redundant. It is dense but appropriately sized for the complexity.

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 3-parameter mutation tool with no output schema, the description covers what the tool does, when to invoke it, how to identify the target post, what will happen after invocation, access restrictions, and the approval behavior. No critical information an agent needs to call it correctly is missing.

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%, so the baseline is 3. The description adds operational value by explaining where pipeline_output_id comes from ('from the post_to_x result or get_pending_approvals') and when it applies. companyId and reason are left to the schema, but the description reinforces the key parameter's origin.

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 names the action ('Hold') the resource ('scheduled X post') and the behavioral outcome ('Puts the post back to pending so the scheduler skips it'). It also distinguishes the tool from approval/publish siblings by framing it as a 'veto lever' and ties it to related tools like post_to_x and get_pending_approvals.

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 gives explicit trigger language: 'Use when the operator says hold, stop, or do not post that.' It also provides routing guidance: use for waiting posts, and for already-published posts it says to delete on X instead. It even states the access boundary: hired agents cannot hold posts.

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