recall

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

With no annotations, the description fully discloses behavior: semantic + keyword matching, search scope limited to specific memory entry types, call frequency, skip conditions, and that 'Knowledge stays in your context.' This is significant context beyond what a schema could provide.

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 description is front-loaded with the core purpose and includes a useful example. It is compact but contains some redundancy (e.g., 'stored memory' vs. 'memory entries') and a restatement of the required parameter, but overall each sentence earns its place.

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-parameter tool with no output schema, the description is self-sufficient: it explains what the tool does, its scope, exclusions, when to call it, when to skip, and provides an example. The behavior is fully contextualized for an agent.

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 baseline is 3. The description adds only an example and repeats 'Required param: context'; it does not enrich parameter meaning beyond what the detailed schema descriptions already provide.

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 specific action: 'surface prior knowledge you haven't loaded yet' and 'Searches stored memory using semantic + keyword matching.' It distinguishes itself from siblings by clarifying scope: 'Searches YOUR memory entries (from learn/gotcha/convention/prefer)' and 'Does NOT search the codebase or the internet.'

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 usage guidance is given: 'Before starting a task' and 'Call once per area.' It also provides clear when-not-to-use instructions: 'Skip if you already recalled this topic or received it from brief().' The exclusion of codebase/internet searches further refines when this tool is appropriate.

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