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

Annotations already declare non-read-only, non-idempotent, non-destructive, closed-world. The description adds the precondition gate (vision probe must have passed) and the return value (an id), which matters since there is no output schema. It stops short of warning that repeat uploads create duplicates or citing the ~11MB size cap, so it is not a 5.

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?

Front-loaded purpose, then two labeled routing lines, then one compact example. No sentence is redundant and the example is the most efficient way to convey the payload shape.

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?

Two parameters, no nested objects, no output schema — and the description still covers formats, precondition, exclusions, return value, and payload example. 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 coverage is 100%, so the baseline is 3, but the worked example adds real meaning by showing that `data` accepts a full data URL ('data:image/png;base64,...') rather than raw base64, and pairs it with `filename`. That resolves the one genuine ambiguity in the schema.

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 and resource (upload a floor/seating plan image), names the accepted formats, and says what it returns (its id). The 'to trace the chart from' clause plus the emphasis on image files makes it distinguishable from read_reference_image, list_reference_images, and begin_vision_probe.

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 explicit 'Use when' condition (user shares a venue plan AND the vision probe has passed) and an explicit 'Not for' exclusion (PDFs, or a plan only seen in chat). The vision-probe precondition correctly routes the agent to the sibling probe tools first.

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