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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is fully covered by structured data. What the description should add for an incremental-fetch tool — what counts as 'new', whether results are relative to the last call or to the 'since' cursor, whether returned items are consumed/marked read, and how results are ordered — is entirely absent.

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?

A single front-loaded sentence with no filler or redundancy. It is efficient, but the brevity comes at the cost of under-specification rather than being genuinely tight prose.

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?

With no output schema and no schema descriptions, the description is the only place an agent can learn what a 'match' object looks like and how incremental retrieval behaves, and it supplies none of that. For a three-parameter polling tool the definition is materially incomplete even though annotations cover safety.

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% across three parameters, so the description carries the full burden and mostly fails it: savedSearchId, since, and limit are never mentioned. Only the word 'new' loosely hints at the temporal role of 'since', and nothing explains that limit is capped at 20 with a default of 20.

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 verb 'Return' plus the object 'new matches' is concrete, and the qualifier 'owned by the authenticated AI client' narrows the scope. However, 'matches' is never tied explicitly to a saved search — the reader has to import that from the tool name — and no sibling tool in the list concerns saved searches, so no differentiation work is done in the text.

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?

There is no statement of when to call this versus alternatives, no mention of the sibling save_search that creates the searches being polled, and no guidance on polling cadence or whether this should be called repeatedly. The only implied usage is 'fetch updates', which an agent must infer.

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