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

With no annotations provided, the description carries the full burden, and it does substantial work: it discloses the hourly computation cadence, that reads are never live, the payload envelope (inputs, severity, confidence, first-seen time), the definition of open vs. resolved, and that ratings are opinions, not predictions or financial advice. It omits auth requirements and rate limits, but for a read-only feed tool the disclosed traits meaningfully shape agent expectations.

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 sentences, front-loaded with the signal taxonomy and followed by attribute and cadence details; there is no filler. The final disclaimer sentence about opinions and non-advice earns its place given the financial-adjacent domain. It is dense but not bloated for the amount of behavioral and semantic context it conveys.

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 5-parameter tool with no output schema and no annotations, the description covers the signal kinds, per-signal attributes, open/resolved semantics, and compute cadence, which is largely sufficient for correct invocation. Minor gaps remain: no mention of ordering, pagination, or what the returned structure looks like beyond the per-signal attributes, and there is no explicit statement about whether omitting 'kind' returns all categories.

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 20%, so the description must compensate, and it does: all six 'kind' enum values are enumerated in prose, 'severity' and 'confidence' attributes are explained, and the open-signal definition effectively clarifies the include_resolved parameter. The asset and limit parameters receive little direct explanation, but the per-coin baseline phrasing partially covers asset semantics.

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 clearly identifies the resource (signals reflecting changes in CoinGraph's stored state) and enumerates six concrete signal kinds, so an agent understands what this tool returns. The phrasing 'What changed in CoinGraph's stored state' is slightly indirect rather than an explicit 'list/get' verb, and it doesn't name sibling tools to differentiate itself. However, the content is specific enough that it is plainly distinct from coingraph_compare, coingraph_diff, and coingraph_evaluate.

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?

Usage context is implied: the description states signals are 'computed hourly from stored rows, never a live read,' which hints an agent should use this for state-derived signals rather than live data, and 'an open signal is one whose condition still holds' implies how to use include_resolved. But there is no explicit statement of when to use this tool versus alternatives like coingraph_diff or coingraph_discover, and no exclusions or conditions are spelled out.

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