recall

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

With no annotations, the description carries the full behavioral burden. It discloses the content returned (findings, decisions, open tasks, notes about module holders) but omits whether this is read-only, any permission requirements, or result-size/limit behavior. Adequate but leaves real behavioral gaps for an annotation-free 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?

Two sentences, front-loaded with the core purpose and content types, then the timing advice. Dense but no wasted filler; the parenthetical content list earns its space.

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 3-param tool with no annotations and no output schema, the description explains what comes back but not the parameters or result format. It covers the 'why/when' well but leaves the 'what arguments/returns' side under-specified.

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% for all three parameters (limit, tenant, subject). The description implicitly maps 'subject' to a person or module but never defines limit or tenant, nor explains syntax. With zero schema help the description should compensate far more than it does.

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 states a concrete retrieval purpose — surfacing findings, decisions, and open tasks from earlier sessions about a person or module — which is a specific verb+resource. It is reasonably distinguishable from write siblings like note_finding, though it never names a sibling tool to sharpen the boundary. The abstract name 'recall' is rescued by the parenthetical content list.

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?

It gives explicit timing guidance ('Call BEFORE planning') and states the rationale (avoid repeating or contradicting earlier work), which is strong context. However, it provides no when-not guidance and does not name alternatives (e.g., knowledge_map, who_knows) that an agent might confuse it with.

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