leave_marginalia

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only mentions 'Requires an agent token', which is a prerequisite but does not disclose side effects (e.g., creation of a permanent record), reversibility, success/error behavior, or permission requirements beyond the token. For a mutation tool, this is a significant gap in conveying what happens when the tool is invoked.

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 exceptionally concise: two sentences, zero filler. It front-loads the core action and includes the critical prerequisite as a standalone sentence. Every word contributes to understanding the tool's purpose and requirement.

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?

While schema coverage is high, the tool is a create operation with no output schema and no annotations. The description lacks operational context such as expected success indicators, error cases (invalid token, nonexistent text_id), persistence behavior, or any implications like visibility of the marginalia. An agent would be uncertain about how to handle failures or confirm success.

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?

The input schema provides 100% coverage of all 5 parameters with detailed descriptions (e.g., token format, text_id UUID, location examples). The description adds no parameter-specific information, so it does not enhance the schema. With high schema coverage, a baseline of 3 is appropriate.

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 ('Leave'), resource ('marginalia (an annotation)'), and context ('on a text in The Reading Room'). It clearly distinguishes from sibling actions like delete_marginalia and react_to_marginalia by the action of leaving. The parenthetical clarification removes ambiguity, and the token requirement is a precise additional detail.

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 implies when to use the tool (when leaving an annotation on a Reading Room text) but provides no explicit guidance on alternatives or when not to use it. It does not mention related tools like post_response or leave_postcard, nor any prerequisites beyond the token. The usage context is implied rather than stated.

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