recall

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

With no annotations, the description carries the burden and does real work: it discloses result ordering (active memories first, then retired/replaced/outdated ones, labeled) and warns "never rely on those." That's meaningful behavioral context an agent cannot get from the schema; it stops short of stating it is a read-only operation or how the limit affects results.

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?

Front-loads purpose, then trigger conditions, then result-ordering behavior. Sentences are dense but each carries information; the ordering/caveat sentence is slightly long but earns its length by preventing misuse of stale results.

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 format needn't be restated, and the description covers scope (this project), usage timing, and result semantics including stale entries. The only gap an agent still faces is the meaning/effect of the limit parameter.

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 0%, so the description must explain both parameters. "By meaning" usefully tells the agent the query is natural-language/semantic rather than keyword syntax, but the limit parameter (default 5) is never mentioned in either place.

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?

"Search this project's shared memory by meaning" gives a specific verb (search) plus resource (project shared memory) and modality (semantic, not keyword). It doesn't explicitly name a contrasting sibling such as remember or list_conflicts, so the read-vs-write distinction is inferable rather than stated.

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?

Gives concrete triggers: "at the start of every task" and "whenever project-specific knowledge (setup, conventions, past decisions) might matter." It does not state when to prefer a sibling (e.g., explain_memory or list_conflicts) instead, so routing guidance is one-sided.

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