recall

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals return format (citations with memory_type, snippet, timestamp, relevance score), result status ('searchable, provisional, or fallback'), dependence on upstream pending_messages, and auto-detection from git remote. This is thorough, though it does not explicitly state that the operation is read-only, which would have been useful. However, the verb 'search' strongly implies no mutation.

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 well-structured, front-loading the purpose and usage, then providing return details, caveats, alternative tool guidance, and auto-detection behavior. Each sentence adds meaningful information—no filler or redundancy. It is appropriately sized for a complex search tool with 12 parameters and no output schema.

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?

Given the tool's complexity (12 parameters, no output schema, no annotations), the description provides a complete picture. It explains what results look like, how to interpret status flags, when to use an alternative, and how space selection works. The schema covers parameter syntax, and the description fills the behavioral and contextual gaps, making the tool fully usable by an AI 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 the baseline is 3. The description adds value by explaining that when both space_id and space_ids are omitted, the tool auto-detects from git remote, and by summarizing the meaning of the relevance-ranked results. It also notes that pending signals may be absent even if extraction is in progress, which indirectly informs the interpretation of parameters like current_time. This goes beyond the schema's straightforward descriptions.

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 opens with a specific verb and resource: 'Search for relevant memories in one or more spaces.' It distinguishes itself from sibling tools like fetch_history by stating that recall is for retrieving context about prior decisions, preferences, and conventions, while fetch_history is for chronological review. This clearly articulates the tool's unique role.

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?

The description explicitly states when to use the tool: 'Use this when you need context about prior decisions, preferences, conventions, or anything discussed in previous sessions.' It also provides exclusion guidance by recommending fetch_history for chronological review or delete verification, and clarifies auto-detection behavior when space identifiers are omitted. This is exemplary usage guidance.

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