recall

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

With no annotations, the description carries the burden. It mentions 'ranked by relevance x recency x confidence' and 'packed into a context budget,' hinting at output truncation and ranking behavior. It implies a read-only operation but does not explicitly state that it does not modify memory. It lacks details on rate limits, authorization, or what happens when the budget is exceeded. This is adequate but not rich.

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 concise sentences, no filler. The first sentence front-loads the core functionality and ranking scheme; the second adds a usage preference. Every word earns its place, making it easy for an agent to parse quickly.

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?

The description covers the tool's essence and a usage preference, and the output schema handles return values. However, it omits any guidance on query syntax, budget_chars limits, or how scope defaults behave beyond the default value in the schema. For a 3-parameter tool with zero schema coverage, this is a moderate gap — the agent can likely call it correctly, but may not optimize parameter choices without more detail.

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 explain parameters. It mentions the scope parameter with its possible values ('team'|'personal'|'all'), which is helpful. However, it does not explain the query parameter (e.g., free text, exact match) or the budget_chars parameter beyond the vague 'context budget.' Since two of three parameters are effectively undocumented, the description fails to compensate for the schema gap.

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 clearly states a specific action: 'keyword search ranked by relevance x recency x confidence, packed into a context budget.' It also specifies the resources searched (team and personal memory) and explicitly contrasts with 'raw search,' distinguishing it from the sibling tool search_memory. This gives an agent a precise understanding of what the tool does.

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 provides a clear usage condition: 'Prefer this over raw search when answering questions.' This tells the agent when to choose this tool over a generic alternative. However, it does not mention other siblings like list_recent or team_context, nor does it specify when not to use it (e.g., for exact matches, use something else). So it has one clear guidance but lacks comprehensive routing.

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