recall

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered; the description still adds real behavioral context: no queuing, no side effects, results ranked best-first with a [0,1] score plus per-channel similarities. The 'no side effects' clause partly restates readOnlyHint, which keeps it just short of a 5.

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?

Four compact sentences, front-loaded with the pull-mode framing and followed by cue constraints and return shape; nothing is padding. Slight redundancy where 'no side effects' echoes the read-only annotation.

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 no output schema, the description still specifies the return contract (up to k memories, best first, score in [0,1], per-channel similarities), and it covers cue combination rules for all 8 parameters. Nothing an agent needs to invoke and interpret results correctly is missing.

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 documents each cue, making 3 the baseline. The description adds genuine semantics beyond it: only the supplied cues are compared, and 'at' should be added only when time of day matters – a non-obvious fusion rule the schema does not convey.

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 ("Deliberately search memories (pull mode)") and immediately names the contrasting sibling mode ("Unlike sense, it never triggers involuntary recollections"). An agent can distinguish recall from sense 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?

Gives concrete when-to-use examples ('what do I remember about Kyoto?', 'what happened at this place?') and an explicit exclusion rule against sense for involuntary recall. It also states the invocation constraint (at least one cue) and when to omit the time cue, leaving little to inference.

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