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

Annotations already cover the read-only/idempotent/closed-world profile, and the description layers substantial extra context on top: pagination via the '[… N characters omitted, continue with offset=M]' marker, the exact completeness scope of every list ('from the oldest version an act was watched from to its newest'), the meaning of `disputed`/`dispute_reason`, the specific reading of `applies_from: unknown`, and the legal-advice disclaimer. These are non-obvious interpretation rules an agent would otherwise misread.

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?

It is front-loaded with the core purpose, and several sentences (the `disputed` definition, the `applies_from: unknown` clarification) genuinely earn their place. But it is a single dense paragraph mixing field semantics, completeness scope, and a legal disclaimer, which is hard to scan for an agent that only needs the invocation essentials.

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?

An output schema exists, so return values need not be described, yet the description still explains the subtle field semantics that the schema cannot. For a high-complexity legal-diff tool this is largely complete, with the main remaining gap being behavior on missing identifiers or empty results.

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%, so the baseline is 3, but the description goes beyond the schema by spelling out the truncation marker produced by `max_chars` (1 to 50000), the paging semantics of `offset`, and the 'counts repeats of one location in one event from 1' definition of `occurrence`. That is real added meaning, though `act`, `version`, and `location` are left entirely to the schema.

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 opening 'One change in full' names a specific verb and resource and enumerates exactly what the record contains (before/after text, cited sentences, signals, gate outcome), so an agent knows what it retrieves. However it never contrasts itself with siblings like get_event, provision_history, or changes_since, so the singular-vs-list distinction must be inferred from the name alone.

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?

The description is rich on output semantics but gives no explicit when-to-use, when-not, or alternative routing. It only references `list_acts` incidentally to explain the `act` key format, not as a selection rule, leaving the agent to infer that this is the detail fetch after a list call.

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