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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description still adds rate limiting, L402 payment requirement, statelessness, and the specific error behavior for missing stratum entries (JSON-RPC invalid-params). That is meaningful behavioral context beyond structured fields.

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 computation and its outputs, then constraints, then alternatives. Dense and mostly waste-free, though the 'Use this tool specifically to compare two point-in-time entries' sentence partially restates the opening.

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 an output schema present, return-value detail is not needed, and the description still covers defaults, ordering, error behavior, payment/rate constraints, and sibling routing. Nothing needed to call it correctly is missing.

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 the schema already documents both parameters, including the sign convention and the 'latest = latest dataset entry, not live chain tip' caveat. The description reinforces the toTarget-minus-fromTarget direction but adds little syntax or format detail the schema lacks; 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 (compute signed deltas) plus the exact resource (two indexed stratum heights/dates) and even enumerates the returned quantities. It clearly distinguishes itself from sibling lookup tools by naming what kind of operation this is (point-in-time comparison).

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?

Explicitly routes the agent: 'Use this tool specifically to compare two point-in-time entries,' then names three alternatives (stratigraphy.get, get_range, get_digest) with the condition that selects each, and adds an exclusion (data ingest is out of scope). No inference required.

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