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

Annotations cover only the safety profile (readOnly, non-destructive, closed-world); the description goes well beyond them by declaring the return shape: one entry per field, newest-first ordering, and values rendered as words rather than raw ERP enum ordinals. With no output schema, this ordering and formatting detail is exactly what an agent needs to interpret 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?

Two sentences, both front-loaded with the most decision-relevant facts (what it returns, in what order, in what format), then an exclusion clause. No filler or redundant restatement of the title.

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 two-parameter read tool with no output schema, the description does a solid job on return semantics and scope. The missing piece is the 'limit' parameter: an agent cannot tell whether omitting it returns everything or a default slice, which matters for a newest-first history. Otherwise adequate.

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 0%, so the description must carry parameter meaning itself. It implies the required assignment_id through 'one assignment,' but says nothing about the 'limit' parameter — no indication of pagination, whether truncation is possible, or how the 1–100 range interacts with the newest-first ordering. Half the parameters remain undocumented in both schema and description.

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+resource pair: the change history of one assignment, including who made each change. It also distinguishes itself from erp_get_assignment by describing change entries (old and new value) rather than current state, and from erp_comment_assignment by explicitly excluding comments.

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 phrase 'one assignment' establishes the single-record scope, and the closing sentence 'Comments are excluded — they are their own tool' routes the agent away from a plausible but wrong sibling. It stops short of an explicit 'use X when you want current values instead' statement, so a small inference is still needed.

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