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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description adds substantial behavior: newest-first ordering, the pre-schema available=false state, the row fields returned, and the fact that tombstone_id and link_version are what an undo must carry. It also flags the untrusted-content risk from customer-provided names and message text, which is a meaningful safety disclosure beyond structured fields.

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 what the feed is, then constraints, then the security note; every clause is dense and purposeful. The long enumeration of returned row fields is somewhat redundant given an output schema exists, which keeps this from a 5.

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 read-only feed with three simple parameters, the description covers ordering, filtering, paging, the unavailable-before-schema case, output shape, undo prerequisites, and prompt-injection risk. Nothing an agent needs in order to call it correctly or interpret results safely is 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?

Schema description coverage is 100%, so the schema already documents kind, limit, and cursor fully. The description only restates 'filter with kind' and 'page with cursor' without adding syntax, defaults, or interaction details beyond the schema, so the baseline 3 applies.

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 org's identity change feed') plus the exact event kinds it contains (link, unlink, confirm, name, unname, combine, create) and the ordering (newest first). This is clearly distinguishable from siblings like list_identity_candidates and list_identity_decisions, which the wording implicitly separates by describing committed change events rather than candidates or decisions.

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?

'Filter with kind; page with cursor' tells the agent the intended usage pattern, and 'Before the schema exists it answers available=false' gives a prerequisite/edge condition to expect. It stops short of explicitly naming alternatives or stating when not to use this feed (e.g., vs. list_identity_decisions), so it is strong context rather than full routing guidance.

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