convention

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

With no annotations, the description carries the full burden and does so thoroughly. It discloses that data persists across sessions, surfaces in brief() and recall(), returns related knowledge, and should store timeless facts rather than ephemeral notes. This goes well beyond the schema and provides excellent behavioral expectations.

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 well-structured and front-loaded with the primary instruction. Some redundancy exists between 'Store facts... not notes' and the subsequent wrong/right example, but each sentence earns its place overall. The length is acceptable given the tool's complexity.

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?

Given the lack of annotations and no output schema, the description is quite complete: it covers purpose, usage, persistence, surfacing, and return value. However, it omits any mention of the 'review-required' flow that the schema's durabilityDecision hints at, and it does not elaborate on how the returned 'related knowledge' might be used, leaving a slight 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?

Schema description coverage is 100%, so the schema already explains all three parameters. The description adds a JSON example and reiterates required params, but does not add significant new meaning beyond the schema. The 'durabilityDecision' parameter, in particular, is not mentioned in the description.

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 clearly states the action ('record a pattern the codebase follows') and the resource ('convention' store), and distinguishes itself from the sibling tool 'prefer()' by explicitly noting that personal style rules should use prefer instead. It also differentiates conventions from session notes with a concrete example.

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?

It explicitly says when to use the tool ('When you notice a pattern the codebase follows') and when not to ('For personal style rules, use prefer() instead'). It further clarifies with wrong/right examples and emphases one insight per call, making the usage context unambiguous.

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