motion_workflow_read_evidence

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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds real behavioral context beyond them: the 2 MB size cap, the accepted formats, the immutability check ('Rejects changed bytes'), and the semantic caveat that reading does not constitute a valid review. This is meaningful added context on top of the annotations.

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?

Four tight sentences; the core action and constraints are front-loaded with no filler. Slightly dense with several constraints packed in, but every sentence carries distinct information.

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 3-parameter read tool with no output schema and no nested objects, the description covers the return payload, format, size limit, input selection rule, and immutability behavior. It is nearly complete; only error-handling outcomes and the meaning of evidenceId remain unstated.

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 only 33%, with only workflowId documented. The description compensates by explaining the mutual-exclusion constraint between evidenceId and referenceIndex and clarifying that referenceIndex is zero-based, which the schema does not convey. It doesn't explain evidenceId's format or sourcing, leaving a small 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?

States a specific verb (Return/read) and resource (attached candidate image or reference image) with format and size constraints (PNG/JPEG, at most 2 MB). This clearly distinguishes it from siblings like motion_workflow_read (workflow metadata) and motion_workflow_attach_candidate (attaching, not reading).

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 important selection rule ('Supply exactly one evidenceId or zero-based referenceIndex') and a caveat ('Reading an image does not itself establish a valid review'), which implies usage context. However, it never explicitly routes the agent between this tool and alternatives such as motion_workflow_read or motion_review_read, so guidance 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.