recall

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

Annotations already establish readOnly, idempotent, and closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that: results are returned as whole messages accompanied by their dates, and the output is capped by a token budget that falls back to a server-side default. It stops short of explaining how relevance is ranked or what happens when the budget truncates 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?

The core one-sentence summary is front-loaded and dense with useful detail, followed by a compact Args block keyed directly to the three parameters. Structure is a Python docstring rather than prose, which is mildly stylistic, but no sentence is wasted.

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 a read-only, idempotent, closed-world annotation set and an output schema that documents the return shape, the description only needs to cover intent, scoping, and budget behavior — all of which are present. A note on ranking or truncation behavior would close the remaining 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 0%, so the description carries the burden, and it does: query is defined as the question (with a concrete example), budget as the maximum tokens returned, and session as an optional conversation id restricting the search. The only soft spot is the budget default, stated as 'the server's budget' while the schema shows default 2000, which is slightly ambiguous but not harmful.

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 gives a concrete verb and resource: find the stored messages from earlier conversations that answer a question, returned whole and with their dates. That is far more specific than the bare name 'recall'. It does not, however, distinguish itself from siblings such as list_memories or fit_context, leaving the agent to infer that this is relevance search rather than enumeration.

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?

Usage is implied: pass the user's latest message as the query, optionally scope to one conversation via session. There is no explicit statement of when to prefer recall over list_memories or fit_context, and no exclusions or prerequisites. An agent can infer the intended use but is not guided among alternatives.

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