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

Goes well beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false) by disclosing that only an unapproved candidate is written, that the original answer is not approved, that prior replacements stay active until separate approval, and that client identity is never inferred. These are exactly the side-effect and scoping facts an agent needs before invoking a mutation.

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 dense sentences, each carrying distinct constraints (preconditions, scope resolution, write semantics, replacement behavior) with the core action front-loaded. No filler, though the sentence count is near the limit for a description.

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 complex nested-schema mutation with no output schema, the description covers prerequisites and post-conditions adequately. It leaves the idempotency contract and the replaces/validity semantics to the schema descriptions rather than covering them itself, which is a minor remaining gap.

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?

With 67% schema coverage and a deeply nested proposal object, the description compensates: 'Selected dossiers are explicit IDs' clarifies the selected_dossiers scope kind, and 'exact source revision' pins down the answerRevision field. It does not explain validFrom/validUntil bounds, replaces, or idempotencyKey usage beyond what the schema already states.

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 precise verb+resource ('propose an immutable reusable answer from the exact source revision'), which clearly separates this from siblings like reuse_library_entry and retire_library_entry. It does not explicitly name the sibling it pairs with (e.g. apply_library_promotion), so it stops short of a 5.

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?

Gives concrete preconditions — 'Requires a current reviewed proof, owner, bounded validity and explicit reuse scope' — and states the workflow context ('Saves an unapproved candidate only, without approving the original answer'). It never names an alternative tool or an explicit when-not-to-use case, so it is context-rich but not fully routing.

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