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

Annotations already declare destructive=true, idempotent=true and closed-world, so the description's job is to add context — and it does: two refusal conditions, a resubmit-the-whole-SVG loop while differences is non-empty, and the note that upload_id keeps the user's approval box short. It does not say what the tool returns or what happens to a previously uploaded drawing when re-sent, despite destructiveHint.

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?

Only three sentences, but the first is a tangled run-on with stacked parentheticals ("however small ([] at shape_misses 0)"), and it front-loads schema-duplicating detail about differences ahead of the harder constraint. Purpose is front-loaded; readability and de-duplication are not.

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 7-parameter, three-required mutation tool with full schema coverage and no output schema, the description covers the iterate-until-clean workflow, the upload path and both refusal gates. The remaining gap is what a successful call returns and whether it overwrites prior artboard content, which matters given destructiveHint.

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 schema already defines the viewBox requirement, the variant two-stage rule, upload_id and the per-part differences list. The description largely restates that (differences = every remaining flaw, [] at shape_misses 0), adding only the rule that watermarks/logos/captions are never listed — marginal net new meaning.

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 action and resource: upload a hand-written SVG onto an image's drawing artboard, and adds a sharp qualifier (hand-written, not auto-traced) that separates it from the generation/compare siblings. It does not name those siblings (compare_drawing, generate_illustration) outright, so routing between them is inferred rather than stated.

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 real conditions: auto-traced output (potrace, vtracer, quantising) is refused, differences must be [] before the drawing counts as finished, and variant is refused until the exact copy is done. It also prescribes the shell alternative (curl the .svg to the upload link from new_project, pass upload_id). No explicit 'use X instead when…' against siblings, which keeps it below 5.

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