coherra_recall

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

With no annotations provided, the description carries the full burden, and it delivers: it discloses the complete return payload (value, confidence, source, created_at, updated_at, version), the exact return envelope, and the NOT_FOUND error condition. The read-only nature is implied by 'Fetch' rather than stated outright, and no auth or side-effect information is given, but for a simple recall tool the disclosed error and return behavior is substantive and above average.

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 with clear sections (purpose, return body, error case, args, returns) and front-loads the core purpose. The Returns JSON block is slightly redundant given an output schema exists, and the return body is described twice, but the overall length is justified and no sentence is wasteful.

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 2-parameter fetch tool, this is nearly complete: purpose, parameter semantics, return shape, and error behavior are all covered. Minor gaps exist — it doesn't state the dependency on coherra_remember (entities must be stored before recall succeeds) or explicitly confirm the operation is non-mutating — but nothing critical is missing for correct invocation.

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 fully compensate, and it does. 'category: The category the entity was stored under' and 'name: The unique-within-category key' add real relational semantics — the agent learns that uniqueness is scoped within category, which is essential for correct use and is not derivable from the bare schema.

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+resource statement: 'Fetch a single Coherra entity by (category, name).' The word 'single' plus the exact lookup key clearly differentiates it from siblings like coherra_list (listing) and coherra_remember (storing). An agent can tell this is the point-read tool without opening any sibling schema.

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 usage context is implied by the phrasing — fetch one known entity by exact key — and the NOT_FOUND error behavior tells the agent what happens when the key is absent. However, the description never explicitly names alternatives (e.g., 'use coherra_list to browse entities' or 'use coherra_remember to store first'), so the when-to-use vs. when-not-to-use guidance is left to inference rather than stated.

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