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

With no annotations, the description carries the full burden and mostly succeeds: it discloses newest-first ordering, prefix-match semantics, 'current-truth' filtering (implying superseded memories are excluded), the shared-brain scope ('no agent filter'), and the provenance/matched_paths payload. It does not mention required permissions, rate limits, or pagination behavior beyond the schema's k.

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 leading sentence is front-loaded with the core purpose and ordering, followed by tight, evidence-dense detail. The parenthetical examples earn their space, though the middle sentence is somewhat run-on and could be split for readability.

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?

An output schema exists, so return-value explanation is not strictly required, and the description still usefully describes the provenance block and metadata.matched_paths. For a read-only, 4-param lookup the coverage is nearly complete, missing only explicit statements of permission requirements and whether the operation is side-effect free.

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 the baseline is 3, but the description adds real semantic value beyond it: it explains the prefix/directory matching rule for paths and how repo-sharing interacts with tag matching, and ties the tag format back to memory_remember(paths=). The k, repo, and github behaviors are largely left to the schema.

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?

States a specific verb and resource ('returns current-truth memories tagged path:<p>') and pins down the exact matching semantics, including that a directory matches files under it and that 'src/billing' will not match 'src/billing2'. An agent can distinguish this from memory_recall (keyword search) without opening either schema.

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?

Explicitly frames the tool as 'An exact path lookup, not search' and names the alternative ('use memory_recall for keywords'), giving both when-to-use and when-not. It also names memory_remember(paths=) as the producer of the data being looked up, closing the loop on the workflow.

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