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

Annotations only mark it as non-read-only and open-world; the description carries far more: exact cost (2 AI credits per call, drawn from the monthly pool rather than the org's own AI key), that no credits are spent without confirm: true, that the unconfirmed call is a pure quote, and the approval/idempotency semantics for repeated calls. That is precisely the extra context annotations cannot supply for a credit-spending tool.

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-loads purpose and cost, then the confirm workflow, with no filler sentences; each clause carries an operational rule the agent must follow. It is dense rather than short, and the final sentence about approval scope is slightly awkward, but nothing is redundant.

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 credit-spending, no-output-schema tool, the description covers the things an agent needs: cost and billing source, the two-phase confirm gate, what the dry call returns, approval scope, and the capability constraint on suggestions. Nothing material is left for the agent to guess.

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 already 83%, so the baseline is 3. The description goes beyond the schema by explaining what confirm actually gates (spending credits, running the action), what the no-confirm call returns (a quote), and that the confirmed re-call must use the same arguments — semantics the one-line schema text only gestures at.

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 ("Propose a ready-to-publish post idea for a given network") and adds a real scoping rule: it is constrained to what the organization can actually produce, with a concrete example about video providers. It never names or contrasts with adjacent idea/content siblings such as plan_content, plan_campaign, or suggest_hashtags, so the boundary is inferable but not explicit.

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 an unusually explicit call protocol: call first without confirm (nothing runs, nothing charged, returns a quote), relay the quote to the user in their own words, then re-call with identical arguments and confirm: true after a clear yes. It also defines the scope of one approval and when a new approval is needed. What it does not do is say when to prefer this tool over sibling idea-generation tools.

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