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

Annotations already establish readOnly/destructive safety, and the description adds meaningful behavior: results are bounded, public, and free of inference/cross-lane synthesis, and upstream unavailability is preserved as typed rather than collapsed. This goes beyond the structured metadata without contradicting it.

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?

Two tight sentences earn their place: the first states scope and exclusions, the second a key error/availability behavior. No filler or repetition of schema details.

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 a rich output schema, safe annotations, and a single optional enum parameter, the description covers purpose, boundaries, and an important upstream-availability behavior. It is missing only explicit lane-parameter semantics and sibling routing, so it is near-complete but not exhaustive.

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 prose needed to explain the lane parameter, but it never mentions 'lane', 'all', 'seiche-summary', or the palimpsest/seiche enum values. The domain labels in the description only indirectly map to enum values, leaving parameter selection semantics mostly to the 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 and resource ('Return bounded public ... context') and clearly defines the tool's lane-scoped read purpose: separate Seiche and Palimpsest evidence without cross-lane scoring or inference. This distinguishes it from synthesis-oriented siblings while matching the title's 'separate evidence lanes' framing.

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 gives an explicit negative usage rule ('without cross-lane scoring, composites, causal inference, or culpability inference'), making clear when this tool is not appropriate. It does not name alternative tools or positive when-to-use conditions, so it stops short of a 5.

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