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

Goes well beyond the readOnly/idempotent annotations: it discloses the 50-row cap with a `more` counter, that `operations` are sampled from the ten newest traced runs (up to five span names per row), the p95 floor caveat above 60s, and that `untrusted_fields` marks externally-written `data`. These are exactly the operational traits an agent needs and cannot get from 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-loads the scope requirement and is dense but earns most of its length by enumerating return fields in the absence of an output schema. The single long clause-list is efficient, though slightly hard to scan.

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 carries the full burden of describing return values and does so thoroughly: field list, metric semantics, sampling, truncation, and data-provenance caveats. Combined with the auth requirement, an agent has everything needed to call and interpret it.

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 100%, so `id`, `range` (with default and UTC-day overlap behavior) and `direction` are fully documented in the schema. The description adds no parameter-level meaning, so the baseline 3 applies.

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?

States a specific verb+resource and scope ('What one agent calls, heaviest first, from its traces'), so an agent knows this is a per-agent dependency listing rather than a global one. It implies the singular scope that separates it from list_dependencies, but never names that sibling explicitly.

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?

Provides the access precondition ('Requires the read scope or higher'), which is genuine usage guidance, but gives no when-to-use/when-not framing or routing to alternatives like list_dependencies or get_agent_usage. Usage is implied rather than stated.

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