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

Annotations declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true, but the description adds material context beyond them: cost ('FREE'), the crucial fact that the live map is untouched while a draft and semantic diff are produced, null semantics for removing settings values, and the invariant that deleting referenced objects requires dependency repair in the same batch. It stops short of describing what happens on a stale expectedRevision, which is the main failure mode of an optimistic-concurrency tool.

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 tight sentences, front-loaded with the most decisive facts (cost, scope, no live mutation, the follow-up tool). No filler, no restatement of the title, and the batch-level constraint about deletions is placed last where it applies to operation content.

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 3-parameter tool with a deeply nested anyOf schema and no output schema, the description covers purpose, cost, side-effect boundary, return shape, and the key batch invariant. Gaps are secondary: no guidance on revision-conflict recovery, draft lifetime, or how to inspect the returned diff before committing.

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 carries the burden and partly compensates: it explains the 200-op ceiling, that operations use stable IDs, the role of expectedRevision, and the null-removal convention for settings values. However, mapId and the conflict-retry meaning of expectedRevision are left implicit, and the seven op variants are only enumerated by the schema's const values rather than in prose.

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 (apply stable-ID operations to a map), the scope (up to 200 ops, gated on expectedRevision), and the return form (validated draft + semantic diff). It also names the workflow partner commit_map_draft, making it distinguishable from siblings like prepare_map_draft, preview_map_draft, and get_map_draft without opening any 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?

'Preview/test then use commit_map_draft' gives explicit sequencing and names the alternative that actually mutates live state. What is missing is any when-not-to-use guidance, e.g. whether this is required before commit_map_draft or how it relates to prepare_map_draft/preview_map_draft, so the routing is clear but not exhaustive.

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