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

Annotations only give the generic safety quadruple (readOnly=false, destructive=true, idempotent=true, openWorld=true); the description adds non-obvious behavior well beyond them: no model invocation, in-place mutation preserving the job id and links, refusal of brief/picture requests, a 20-edit cap, and the fact that the response returns the full current spec in `intent`. This is real behavioral payload, not restatement.

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?

Five short sentences, each carrying distinct information (in-place/free, params, refusal, response shape, edit cap) with the core action front-loaded. No filler or repetition.

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 mutation tool with a deep nested patch schema and no output schema, the description closes the gaps that matter: it names the return field (`intent`), the no-model refusal path, and the edit ceiling. An agent has everything needed to call it correctly.

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% and the patch schema is exhaustively annotated, so the baseline is 3; the description adds only light context ('Send the job_id and a patch of the fields to change', and that the response carries the spec as `intent`). It names the response field but leaves the rich null-removes/list-replaces/merge semantics to 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+resource: 'Change a slide you already rendered, in place.' It immediately distinguishes itself from create_slide by scoping to an already-rendered slide keyed by job_id, so an agent can pick it without opening either 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?

Explicitly covers the when ('a slide you already rendered'), the when-not and alternative ('Never runs a model: a brief or a picture request is refused — make a new slide for those'), and a hard limit ('Up to 20 edits per slide'). Nothing about tool selection is left to inference.

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