recall

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

With no annotations, the description carries the disclosure burden and does meaningful work: it states that long memories return only the matching segment rather than the whole record, and that output is capped by max_chars (default 12000, ceiling 30000). What it omits is scoring/ranking behavior or ordering of results, which matters for a semantic search tool.

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?

Purpose and when-to-use are correctly front-loaded and there is little outright padding. However, the section sentence is grammatically broken ('section keeps one part of memory, e.g. for ...'), and the clause about recall_full reads as a fragment, forcing the agent to re-parse intent.

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 detail is unnecessary, and the description covers truncation, the size cap, and section values. The remaining gap is 'k' and result ordering — meaningful for a top-k semantic search over memory — but the definition is otherwise sufficient to invoke the tool correctly.

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 must compensate and largely does: it enumerates plausible section values (projects, prefs, reference, about, people, personal) that the schema lacks as an enum, and supplies the max_chars default and hard ceiling of 30000. The 'k' parameter is never mentioned, leaving one of four parameters completely unexplained.

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?

Opens with a specific verb+resource: 'Search long-term memory by meaning and keywords', which is concrete and distinguishable from a pure ID fetch. It also points at recall_full for retrieving a whole memory, giving a sibling contrast, though the phrasing 'recall_full ID gives one whole' is garbled enough to blunt the differentiation.

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?

Explicit when-to-use is given: 'Use before answering anything that may depend on the user's past preferences, people, projects or decisions', plus a concrete example query ('what do you know about X'). It also implies the alternative for whole-memory retrieval, though it never states when NOT to search memory (e.g. current-turn data only) so it stops short of full routing guidance.

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