apply_settings

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the mutation/safety profile is known. The description adds genuinely useful behavior beyond that: the batch is atomic (all-or-nothing), it writes to a new revision, and it 'never overwrites the source.' It does not mention validation failure behavior or any permission requirements, so this is solid added context but not rich.

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?

The action and its atomicity are front-loaded, and each subsequent sentence carries a distinct value rule (JSON types, percent strings, scope semantics, source preservation). It is dense but every sentence earns its place; there is no filler.

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 nested objects, 0% schema coverage, no output schema and no annotations about return shape, the description covers atomicity and value-type rules well. It leaves gaps on the meaning of target/revision/project_id and on what a successful or failed apply returns, which an agent calling a batch-apply tool would benefit from.

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% and all five parameters carry only titles, so the description must compensate. It partially does: it explains scope-dependent value semantics (filament scope selects one existing filament_index, project scope requires complete vector arrays) and percent-string rules. However, target, revision and project_id go unexplained and are never mapped to behavior.

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?

The description uses a specific verb+resource: 'validate and apply an atomic batch to a new revision.' That clearly frames a mutation against a revision and is distinguishable from the read-oriented sibling get_settings and from restore_revision. It stops short of describing what 'settings' are, but the action and scope are unmistakable.

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?

There is no explicit when-to-use statement and no naming of alternatives such as get_settings (to read) or restore_revision (to roll back). The constraints given are correctness rules for values, not routing guidance, so an agent gets no help choosing between this and its siblings.

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