find

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

With no annotations, the description carries the full burden. It discloses determinism, current-value semantics, and null behavior. While it does not explicitly state it is read-only, the read nature is clear from 'Exact key lookup' and 'reads back', which is sufficient for a simple lookup 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?

The description is a single, well-structured sentence with a colon and dash, front-loading the core purpose. Every phrase adds value, with no filler.

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 simple two-parameter read tool, the description is complete: it states the return value, null behavior, and deterministic nature. The reference to upsert provides relationship context, and no output schema is needed for such a straightforward tool.

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. It names (namespace,key) and explains that the value is stored under this pair, giving meaning to both parameters. However, it does not elaborate on allowed namespace values or format, leaving some gaps.

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 the tool performs an exact key lookup, specifying it returns the current value under (namespace,key) or null. It explicitly distinguishes itself from fuzzy recall, separating it from sibling tools like recall.

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 says when to use this tool (deterministic point-read vs fuzzy recall) and identifies it as the complement to upsert ('reads back what upsert wrote'). It explicitly contrasts with 'not fuzzy recall', providing a clear when-not and alternative.

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