run_hooks

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

Annotations declare readOnlyHint=false and openWorldHint=true, so the agent knows state is mutated and external side effects are possible; the description's 'newer than each hook's last one' adds useful context about a per-hook cursor. However, it never states whether events are consumed/acknowledged (i.e., whether a second call re-delivers the same events), nor does it warn about outbound calls, latency, or partial failures — the key behavioral facts for a non-read-only, open-world tool.

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?

One front-loaded sentence with no filler; the scope ('every saved hook') and the incremental semantics land immediately.

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 zero parameters and no output schema, the description carries the burden of explaining the response — and it only says 'deliver the events'. It does not indicate the shape of the result (per-hook grouping vs flat list), what happens for hooks with no new events, or how errors on individual hooks are reported.

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?

The tool takes no parameters, so there is nothing to disambiguate; the description correctly implies the operation is global across all saved hooks with no filtering argument.

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?

Specific verb ('evaluate') plus resource ('every saved hook') plus the effect ('deliver events newer than each hook's last one'), which is far more informative than the bare name. It implicitly distinguishes itself from list_hooks/create_hook/delete_hook by being an execution action, though it never names those siblings explicitly.

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 'now' hints at an on-demand trigger and 'newer than each hook's last one' hints at incremental polling, but there is no explicit when-to-use/when-not or guidance such as 'use list_hooks to inspect configuration instead'. Usage is left to inference.

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