changes

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: the default window (last 7 days), the ordering (oldest first), and the exact fields returned. It stops short of stating that this is a read-only operation, any result cap or pagination limits, or timezone assumptions.

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?

One front-loaded sentence that leads with the question the tool answers and puts the enumeration of return fields last. The parenthetical with three time formats is dense but each clause earns its place; only a small amount of readability is sacrificed to compactness.

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 one-optional-parameter changelog with no output schema, the description covers input formats, default scope, ordering, and the returned field set. The only gaps are volume/pagination expectations and any statement of read-only guarantees, which are minor for this complexity.

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 0% and the lone `since` parameter is an untyped anyOf with no description, so the description is the only source of semantics. It fully compensates by listing the accepted formats (ISO time, epoch ms, or relative 7d/12h) and the default of the last 7 days, which is everything needed to call the tool correctly.

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 names the resource (Canon) and states exactly what it returns: a change log with at, subject, predicate, old, new, by, and the deciding decision. That is a clear verb-plus-resource purpose. It loses a point only because it never distinguishes itself from the adjacent fact_history sibling, which an agent could easily confuse with this changelog.

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 is implied rather than stated: query what changed since a point in time, defaulting to the last 7 days. There is no explicit when-not guidance and no named alternative (e.g., fact_history for a single fact's lineage), so the agent must infer routing from the sibling list.

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