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

Annotations already establish read-only, idempotent, non-destructive behavior, so the bar is lower. The description adds genuinely useful context — results are aggregates, scoping is by block or run, defaults apply on omission, and legacy tests are supported — but says nothing about auth requirements, metric freshness, or how legacy behavior differs.

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 short sentences, front-loaded with the capability statement, followed by input sourcing and legacy support. Nothing is padded, though the trailing 'Legacy tests also supported' is thin enough to be nearly 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?

An output schema exists, so return values need no explanation. The description covers input sourcing, default behavior, and legacy compatibility, which is most of what an agent needs; the remaining gap is the absence of disambiguation from the non-human navigation siblings.

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 only 33%: blockId is documented in-schema, while runId and the required testId carry only patterns. The description partially compensates by explaining how block/run IDs are sourced and what omission means, but it never clarifies testId usage even though it is the only required parameter.

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 and resource — 'Read aggregate navigation metrics for human sessions' — which cleanly separates it from raw-session tools like get_human_session and from the aggregate get_navigation_summary. However, it never names that sibling or states the human-vs-other distinction explicitly, so differentiation is inferred rather than asserted.

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?

'Use IDs from list_test_blocks to target a block/run' routes the agent to the correct source for inputs, and 'omission uses the documented defaults' describes fallback behavior. But there is no explicit when-to-use-this-instead-of guidance against get_navigation_summary or get_human_session, leaving the choice of tool to inference.

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