proofpage_draft_example

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that drafts are created in an 'unapproved' state and that the tool cannot approve or export training data, which is meaningful authority-boundary context. It omits permissions needed, idempotency, duplicate handling, and side effects of creating a draft.

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?

Two dense sentences with the creation action and its scope front-loaded, followed by the key constraint. Every clause contributes information and there is no filler.

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 tool with five required parameters, a nested object, zero schema descriptions, no annotations, and no output schema, the description is too thin. An agent still cannot tell what shape 'payload' expects or what 'revision_id' refers to, which is critical for invoking the tool correctly.

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 0%, so the description must compensate, but it only partially does. It gives real meaning to 'kind' by enumerating SFT/preference/correction/evaluation and to 'quote' by requiring an exact evidence quote, but 'revision_id', 'notes', and especially the nested 'payload' object are left entirely unexplained.

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 states a specific verb and resource ('Create an unapproved ... draft') and enumerates the four draft kinds (SFT, preference, correction, evaluation), so an agent knows exactly what this tool produces. It does not explicitly differentiate itself from any named sibling, though no sibling creates drafts, so the risk of confusion is low.

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?

Usage is implied through the precondition 'tied to an exact evidence quote' and the limitation 'Cannot approve or export training data', which suggests where the tool's responsibility ends. However, no explicit when-to-use or when-not-to-use guidance is given, and no alternative tool is named for approving or exporting.

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