recall

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

With no annotations, the description carries the full disclosure burden, and it does add genuine behavior: include_history replaces each hit with its supersedes chain, and history_depth caps how many versions back are traversed to keep the response small. It says nothing about ranking/scoring method (semantic vs keyword), permissions, or the shape of a returned MemoryNode.

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 core purpose is front-loaded in a single sentence, and the follow-up paragraph is scoped to one behavior. The '(CoMeT-style)' citation is jargon that earns no place for an invoking agent, a minor cost against otherwise tight prose.

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 no-annotation, no-output-schema search tool, the definition covers result-shaping behavior but omits what comes back (MemoryNode structure, ordering/ranking of hits) and the meaning of k. An agent can call it, but cannot predict the response well enough to plan downstream steps confidently.

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 compensate, and it does for two of four parameters: include_history and history_depth both receive real semantic content (chain expansion and version budget). 'query' is only described as free-text relevance search, and 'k' — the hit count, default 5 — is left entirely unexplained by both schema and 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 first sentence names a specific verb (find) plus the resource (MemoryNodes) and the retrieval method (relevance to a free-text query), which distinguishes it from the mutation siblings remember/forget and from the id-based get_node. It does not explicitly state the contrast with get_node or stats, so the differentiation is inferred 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?

There is no explicit 'use this when... instead of X' guidance against the four siblings. The one real usage rule given is conditional and tied to a flag: setting include_history=True when the agent wants the story rather than the latest state. That is useful but covers only one mode of invocation, leaving the choice between recall, get_node and stats to inference.

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