Draw Circles (bulk)

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

Annotations only declare it is a non-idempotent, non-destructive write; the description adds real context — it targets the most recent sketch, defers the re-solve across all inserts, and restores prior state afterwards. 'Restores the previous state' is left ambiguous (undo state vs sketch state) and nothing is said about partial-failure rollback, which keeps it off 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?

Purpose is front-loaded in the first clause and the performance benchmark justifies its length rather than padding it. The middle clause on superlinear re-solve is somewhat technical but earns its place as the rationale for using the bulk variant.

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 6-parameter geometry mutation with no output schema and thin schema coverage, the description is silent on the resulting geometry (where the row starts, how it is oriented relative to the requested centre) and on return values or error behavior. The performance rationale is strong, but an agent still cannot predict the produced layout from the text plus schema.

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 only 33%, so the description must carry parameter meaning — and it mentions no parameters at all. It never explains the row's origin (center_x/center_y), whether spacing is edge-to-edge or centre-to-centre, or how axis interacts with the layout, leaving half the parameters undocumented in both places.

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 ('Add several equally spaced circles'), names the target ('the most recent sketch'), and the bulk scope cleanly separates it from the single-shot draw_circle sibling. An agent can tell what will be produced without opening the schema.

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?

Implies the when-to-use rule clearly: use this instead of one call per circle when entity counts are high, backed by the 68 ms vs 912 ms comparison. It never explicitly names draw_circle as the alternative for a single circle, so the routing rule is inferable rather than stated.

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