Supersede workfile memory

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

Annotations declare readOnlyHint=false and destructiveHint=false, which already convey this is a write operation that isn't destructive. The description adds atomicity ('update both sides atomically') and the non-deletion detail, which is genuinely useful. However, it doesn't disclose behaviors like whether the operation requires additional permissions, whether it's reversible, or what the response shape validates—though the output schema partially covers the latter.

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 clause adds value: atomicity, prerequisite ordering, non-deletion behavior, and ID persistence. Front-loaded purpose with critical behavioral caveats following. No wasted words.

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 full schema coverage and an output schema present, the description covers the core semantics well: atomicity, prerequisite, and non-destructive nature. It could mention reversibility or permission requirements for full completeness, but for the complexity level this is solidly complete.

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 all three parameters already have descriptions in the schema. The description reinforces that replacementId 'must already exist' and explains the expectedRevision 'revision string' guard (concurrent edit protection), which adds semantic meaning beyond the schema. With full schema coverage, this is the appropriate baseline 3 with slight credit.

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 states a specific verb ('supersede') and resource (memory records), and clearly explains the binary relationship: one record supersedes another with both sides updated. It distinguishes itself from siblings like project_memory_graduate and project_memory_patch by framing the action as a pair-wise replacement rather than a single-record modification.

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 explicitly instructs to 'Create the replacement first' as a prerequisite, and explains the important exclusion: 'neither record is deleted, so the superseded one stays readable and its ID keeps resolving.' This gives clear when-to-use framing and sets expectations about alternative behaviors (non-destructive) that differentiate it from delete-like operations.

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