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

The annotations already declare readOnly, idempotent, and non-destructive behavior, so the description is consistent and adds little beyond the word 'bounded'. It does not explain pagination, consistency guarantees, or whether repeated reads return the same results.

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?

The description is a single short sentence with no redundant wording. However, the phrasing is dense and relies on undefined terms like 'canonical', so it is concise but not optimally clear.

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?

The description does not explain what a change feed entry looks like, what 'evidence changes' means, how results are ordered, or whether there is any continuation mechanism. Given the tool's purpose, this leaves important usage context 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?

The only parameter, limit, is not explicitly described; 'bounded' hints at limiting results but does not state that limit controls the maximum number of feed items returned. The schema provides min/max/default constraints, but the description adds almost no semantic value for this 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?

The description says 'Read the bounded canonical change feed', which identifies a read operation and the general resource, but 'bounded canonical change feed' is jargon and only indirectly connected to evidence through the tool name. It does not clearly distinguish this from sibling tools like get_entity_evidence or search_entities.

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?

No guidance is given about when to use this tool instead of alternatives, such as for incremental synchronization or polling recent evidence updates. The description lacks context about ordering, cursor use, or how this feed should be consumed.

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