Graduate a learning

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

Annotations declare readOnlyHint=false, so it's clearly a write operation. The description adds the key dependency constraint (target must pre-exist) and the expectedRevision param is documented in the schema. Since annotations already establish the mutation context and the schema covers revision guarding, the description adds meaningful context with the prerequisite rule.

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 description is two tight sentences with zero filler. It front-loads the action and adds the critical prerequisite in the second sentence. Only minor credit lost for not structuring the prerequisite as an explicit 'When to use' framing.

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?

With full schema coverage, an output schema present, and annotations clarifying it's a non-readonly write, the description covers the core workflow (create target first, then graduate). The completeness is strong given what structured fields already provide, though it doesn't describe what happens to the learning's state beyond 'graduated'.

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 coverage is 100%, so all three parameters (id, targets, expectedRevision) are documented in the input schema. The description adds context about targets being conventions/decisions/documents and the expectedRevision referential integrity behavior, but the schema already explains these thoroughly. Baseline 3 for full schema coverage is appropriate.

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+resource (graduate a learning/mark as graduated and link it to the target record). It clearly distinguishes from siblings like project_memory_supersede (which likely supersedes a learning differently) and project_memory_patch. The 'mark as graduated and link to durable rule' phrasing is specific.

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 gives clear guidance to create the target record first ('graduating points at something that must already exist'), which is a critical prerequisite. However, it doesn't explicitly contrast with alternatives like project_memory_supersede or state when to graduate vs supersede, which would push to a 5.

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