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

With no annotations provided, the description carries full burden. It clearly discloses mutation (reverts/restores content), the version limit (last 10), ownership requirement, and error behavior (not-found for unknown recording/version). This is solid behavioral disclosure. Could be slightly higher if it noted data loss implications or whether revert itself creates a new snapshot, but current coverage is good.

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?

Three sentences, no filler. Every sentence adds value: what it does, how the versioning works, and the ownership/error behavior. Front-loaded with the primary action. Zero waste.

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?

This is a moderately complex tool (revert semantics with versioning) but has only 2 well-documented params and no output schema. The description covers: the operation scope, snapshot mechanics, ownership constraint, and failure modes. Completeness could improve by noting whether the revert itself pushes a new snapshot onto the version stack (which would affect state), but the description is substantially complete for an agent to use 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 description coverage is 100%, so both parameters are already documented in the schema. The description adds the semantic that 'version' references a snapshot number and that 'recordingId' identifies the recording, but beyond that it doesn't add format/syntax details the schema lacks. Baseline 3 is appropriate given full schema coverage.

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?

Description clearly states the verb ('Revert'), resource ('test recording'), and specific scope: restoring steps and meta (name/category/tags) from a stored version snapshot. It distinguishes from siblings like flow_recording_save, flow_recording_get, and flow_recording_delete_step by specifying it's a version-restore operation. Clearly a revert/undo action within the flow_recording family.

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 description explains the snapshot mechanism (written on every mutating save, last 10 versions kept), which gives the agent context for when this tool is applicable. It also mentions ownership constraint (must belong to authenticated user) and not-found behavior. However, it doesn't explicitly state when NOT to use it or nominate alternatives (e.g., using flow_recording_save to save a new version instead), so it lacks the explicit exclusion/differentiation that would earn a 5.

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