plan_edit

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false; the description usefully adds that resolution happens via a rule engine or a local/remote LLM, which explains the non-idempotency. However, it never states that the 'apply' path actually mutates project state, nor whether that write is reversible or what gets overwritten.

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?

Two compact sentences, front-loaded with the core transformation and grounded by one well-chosen example. The parenthetical about LLM backends is slightly parenthetical clutter but still earns its place by explaining variability.

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?

This is a mutation-capable tool with no output schema and 0% schema description coverage; the description should at least clarify the apply flag and what a returned plan looks like. Neither is covered, so an agent cannot confidently choose apply=true versus reviewing first.

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 0%, so the description must carry the load. It does add real meaning for 'request' via an illustrative example, but 'apply' and 'project_id' are never mentioned — the most behaviorally significant flag is left undocumented.

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 transformation: natural-language request into editable steps, with a concrete example. It implicitly contrasts with the applying siblings ('Review, then apply') but never names edit_project or apply_preset, so the boundary 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?

'Review, then apply' sketches a two-phase workflow, implying this is the planning entry point before mutation. There is no explicit statement of when to prefer this over edit_project, apply_preset, or match_style, and no prerequisites or exclusions are given.

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