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

Annotations provide only false hints (not read-only, not idempotent, etc.), so the description carries the burden of disclosing behavior. It does so thoroughly: explains role-based visibility, the `needs_help` work queue, the handling of sponsor rows where org doesn't match, and that builders who never called the mark tool appear as `unanswered`. It also lists the return fields. This goes beyond the annotations and gives the agent a full picture of what to expect.

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 long but each sentence adds essential role/edge-case detail. It is front-loaded with the core purpose, then expands logically through role differences, denominator, return values, and scope. There is minimal repetition, and the structure flows well. It could be slightly more concise, but it earns its 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?

Given the tool's complexity (multiple roles, conditional behavior, edge cases) and lack of an output schema, the description is exceptionally complete. It describes the returned fields, the meaning of `unanswered`, the sponsor edge case with the fix, the `needs_help` work queue, and the required scopes. An agent can invoke it correctly and interpret results without additional documentation.

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?

With 50% schema coverage (only `needs_help_only` has a description), the description only mentions the args generically as `{ eid?, needs_help_only? }` and adds context for `needs_help_only` by explaining it filters to builders with a blocked mark. But `eid` is completely unexplained, and the description does not compensate for the missing schema coverage for that parameter. The agent is left guessing what `eid` refers to (likely event ID), which is a significant 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?

The description clearly states this is a credits checklist across the whole builder roster, and differentiates it from sibling tools like `ic_hack_credits_mark` and `ic_hack_credits_list` by explaining it provides a board view with role-based visibility. It names the resource (credits) and the action (view/get), and the scope is clear.

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?

The description gives explicit when-to-use guidance, including role-specific behavior (organizers get named rows, sponsors only see counts on their own offer), and explains the denominator is the roster, so users should use it to find unanswered builders. It also notes the required scopes and the fix for mismatched org, and distinguishes staff-only behavior for `needs_help_only`. This is comprehensive and clearly routes the agent.

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