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

Goes well beyond the readOnly/non-destructive annotations: ordering (oldest first), field-names-not-values, ~1 minute propagation delay, 30-day retention, cursor never skips a change, and what to do when a cursor is older than oldest_cursor. Missing only details like page-size exhaustion behavior or whether deleted records include a tombstone identifier.

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?

Front-loaded with the core definition, then paging mechanics, retention, and a labeled 'When to use' plus example. Dense but every sentence carries operational meaning; only the trailing example question is optional garnish.

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 4-param, zero-required polling tool with an output schema, the description covers the full mental model an agent needs: what is in each entry, ordering, latency, retention window, cursor lifecycle, and the recovery path when a cursor is stale.

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 baseline is 3; the description still adds real semantics by explaining that next_cursor is echoed back as cursor, that cursor takes precedence and a first call starts at since with a 24-hour default. It does not add anything about limit or object_types beyond 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?

States a specific resource (the workspace's change feed) with its scope and shape: records created/updated/archived/restored/deleted on any object, with field names but never values. Clearly differentiates from sibling readers like get_record and search_records, which it names for fetching records themselves.

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?

An explicit 'When to use' section targets the sync/change-detection case and excludes the alternative ('instead of polling searches or reports'). It also routes the agent to get_record for the actual record bodies, so the choice between the two sibling tools is unambiguous.

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