Read the evidence ledger

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

Annotations already cover read-only/idempotent safety, but the description goes well beyond them: it explains the hash-chain provenance (payloadSha256, previousChainHash, chainHash), that unknown id/lane is refused with an error naming it, that the tool works without an API key on the free tier, and that the unfiltered call is large. The only redundancy is restating read-only/idempotent, which does not undercut the added context.

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?

A single dense paragraph that is well front-loaded: retrieval modes first, then usage, then constraints and return shape. Most sentences earn their place, but the 'Returns {count, records[]}...' sentence partially duplicates the available output schema, and 'Read-only and idempotent' repeats the annotations.

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 2-parameter read tool with an output schema, the description covers everything an agent needs: the three call shapes, precedence and mutual exclusion, the precondition for lane slugs, error behavior for unknown keys, auth requirements, and the size caveat. Return-value detail is largely carried by the output schema.

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% and the schema already documents id precedence and lane origin, so the baseline is 3. The description adds the mutual-exclusion rule ('pass id or lane, not both') and the consequence of passing neither (the entire, large ledger), which the schema does not state, nudging it above baseline.

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?

Opens with a specific verb and resource ('Read the hash-chained evidence ledger') and immediately names the three retrieval modes (by id, by lane, whole chain). It explicitly routes to the sibling pulse_lanes for lane slugs, so an agent can distinguish it from the other pulse_* tools without opening a schema.

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?

States concrete when-to-use cases (verify a claim before relying on it, cite sources, audit for tampering), names the alternative for lane discovery (pulse_lanes), states the mutual-exclusion rule ('pass id or lane, not both'), and steers away from the no-argument case because the full ledger is large. Nothing is left to inference.

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