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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely useful behavior beyond them: the required read scope, a hard cap of 200 results, the most-recently-seen ordering, and an explanation of what untrusted_fields means (fields LastPing did not write). That is real context an agent cannot get from the annotations.

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?

Front-loaded with the auth requirement and then the resource definition, and every clause carries information. Slightly penalized for the broken fragment about 'traces that arrive while no agent shows them', which adds words without adding clarity.

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 zero-parameter, no-output-schema tool, the description does the heavy lifting: it defines the resource, the returned fields, the cap, the ordering, and the untrusted-field caveat. Only the muddled usage sentence and the absence of any pagination/continuation guidance keep it from a 5.

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?

With zero parameters declared, the baseline is 4. The description compensates by documenting the shape and semantics of the response payload, including the meaning of suggested_agent_id and untrusted_fields, which is more than the empty schema supplies.

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 names a specific verb+resource and narrows scope precisely: 'Trace sources that sent spans but match no registered agent', which cleanly distinguishes this tool from list_agents and the rest of the sibling list. It even enumerates the returned fields (id, source_name, first/last seen, span_count, suggested_agent_id), so an agent knows exactly what it gets.

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 references the alternative ('adopt_discovered_agent counts a source under an agent') and gestures at the operational context, but the pivotal sentence — 'For traces that arrive while no agent shows them' — is a fragment that never states a clean when-to-use condition versus list_agents. Usage is implied rather than spelled out.

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