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

Annotations already declare non-read-only, idempotent, destructive, and non-open-world, and the description adds real depth beyond them: the optimistic-concurrency rule (document.revision must equal expected_revision + 1), the retry semantics of a repeated request_id, the validation envelope (slugs, HTTPS origins, official Meta event names, path without query/fragment), and the return payload. It does not explain what the destructiveHint=true annotation actually destroys (presumably a prior draft), which is the one gap.

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?

Front-loads the purpose and the scope exclusion before the constraint list, and every clause carries a real constraint. It loses a little efficiency by restating the document object shape ({schemaVersion, revision, conversions:[...]}) that the schema already expresses structurally, but the accompanying semantic rules are not duplicative.

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 nested 3-parameter mutation tool with no output schema, the description covers inputs, validation limits (1-50 conversions, 1-20 targets, 100 total, 32 KiB), and even the return values (saved proposal, open questions, review link). The only incompleteness is that the destructive annotation is left unexplained relative to a 'draft' save.

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 full burden and largely succeeds: it defines the document shape, the relationship between expected_revision and document.revision, the idempotency meaning of request_id, and semantic rules for ids, labels, event names, origins, paths, and success kinds. It could have added per-field meaning for expected_revision on a fresh site (0), but the concurrency formula covers the essential case.

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 ('Saves a conversion plan draft for the connected site') and immediately bounds the scope with 'Does not approve or activate it', which cleanly separates it from the approve_conversion_plan / approve_and_start_conversion_plan siblings. An agent can route between draft-saving and approval 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?

The negative scoping ('does not approve or activate') tells the agent this is the draft path and implies the approval siblings handle the other path, and the revision/idempotency rules give operational context for calling it. However, no alternative tool is named explicitly and there is no statement of when to choose this over read_conversion_plan or stage_conversion_installation.

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