atcCentralResult

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

Describes that the result is persisted, returned compact, and includes itemId/index, location, processor, lastChangedBy. Discloses truncation behavior and filtering options. No annotations provided, so description carries full burden and does so well, though could mention it is a read-only operation.

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?

Three sentences: first defines main purpose and return format, second distinguishes from sibling, third details findings. Efficient, front-loaded, 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?

With no output schema, the description adequately hints at return structure (summary + per-object findings with key fields). All five parameters are described. Sibling distinction covers the most relevant alternative. Minor gap: does not state that the call has no side effects, but implicit from 'reads'.

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 coverage is 100%, baseline 3. Description adds meaningful context: displayId format (32-char hex), objectName recommended, maxFindings default 200 with truncation flag, includeExempted purpose. Exceeds minimal schema documentation.

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?

Clearly states it reads a persisted central ATC result by display ID, returns compact summary with per-object findings. Distinguishes itself from sibling atcWorklists by specifying the latter only works for transient tokens.

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?

Explicitly says when to use this tool (for CENTRAL runs) and when not to (use atcWorklists for transient tokens). Provides guidance on recommending objectName filter for large results.

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