Operator: Manage Stakes

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

Annotations carry only a title, so the description bears the full transparency burden. It fully discloses the requirement for CIVITAE_ADMIN_KEY, the irreversibility of settle and refund, that these are permanent financial operations, and that they are logged in the audit trail. List mode is explicitly flagged as read-only. This is exemplary behavior disclosure.

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 content is organized with a strong front-loaded summary, followed by requirements, operation semantics, safety warnings, and sibling routing. Every sentence contributes useful information; there is no filler or repetition of schema content.

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 has three distinct modes with different side effects and no annotations to carry safety info, the description covers prerequisites, parameter behavior, irreversibility, logging, and sibling alternatives. An output schema exists, so omitting return-format details is acceptable. Nothing an agent needs to call this 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 description coverage is 100%, so the baseline is 3. The description goes beyond the schema by clarifying that list mode shows pending stakes specifically, and by giving concrete examples of when to settle ('work is completed') versus refund ('terms are not met'). This adds operational meaning beyond the raw parameter descriptions.

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 opens with a specific verb and resource: 'manage stakes — list pending, settle (release funds), or refund.' It clearly distinguishes the tool from operators of reviews, audit, and stats by naming those siblings. This makes the tool's purpose unambiguous and immediately discriminable.

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 explicitly states when to use this tool (operator-side stake management) and when to use alternatives, naming civitae_op_reviews, civitae_op_audit, civitae_op_stats, and civitae_stake. It also clarifies that list is read-only while settle/refund are write operations, giving an agent clear decision criteria.

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