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

Beyond the readOnly/idempotent annotations, the description discloses what is redacted (free text, links, addresses, provider identifiers), what is explicitly NOT done (sends, retries, acknowledgements, writes, provider calls), and that stored provider acceptance is distinct from business resolution. The cursor-binding and empty-page paging semantics are exactly the sort of behavioral detail annotations cannot carry.

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?

Purpose is front-loaded and every subsequent sentence carries a constraint, permission, or privacy rule rather than filler. Some phrasings are compressed to the point of being cryptic ("Stored provider acceptance is separate from read/business resolution (unknown)"), which costs a little readability without adding waste.

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 list tool with no output schema, the description covers permissions, redaction, paging, and the absence of side effects — close to what an agent needs to call it safely. The missing pieces are the limit parameter's meaning and any hint about the shape of returned alert metadata.

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 schema gives no descriptions, so the description must compensate. It explains cursor behavior (binds tenant, actor and grant; must be followed even on empty pages) but says nothing about limit — no default, no mention of the 50 ceiling — leaving one of two parameters undocumented. Partial compensation only.

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?

"Read existing tenant notification ledger metadata only" names a specific verb, resource and a hard scope boundary (metadata only). It does not name the sibling get_alert for single-alert retrieval, so the reader must infer that split, but the operation itself is unambiguous.

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?

Prerequisites are stated precisely (active owner/manager, communications:read, exact own actor binding for private agent alerts), which tells the agent when the call will succeed. However, there is no explicit guidance on when to use list_alerts versus get_alert or other listing siblings, so the choice is only implied.

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