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

Annotations declare readOnlyHint=false but say nothing about why; the description explains the read pointer: each call consumes matches, moves the shared cursor past them, and is shared across sessions. It also discloses peek=true and since_hit_id=0 replay semantics and the Keeploop Pro requirement, all 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?

Two dense sentences, front-loaded with the core behavior, then parameter semantics. Every clause earns its place, though the packing of cursor rules into one sentence makes it slightly harder to scan.

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?

An output schema exists so return shape needn't be explained, and cursor/mutation behavior is thoroughly covered. The only gap is limit (default 25) and any hint about pagination limits interacting with more=true.

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%, so the description must carry the load: it explains peek, since_hit_id (including the 0 replay edge case), and route (routes= source plus the 'duet:<channel>' convention). The limit parameter is never mentioned, leaving one of four undocumented.

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 verb+resource: collect new matches from every monitor carrying a route, oldest first. It distinguishes itself from check_monitor implicitly by scoping to routes rather than a single monitor's token, and defines the cursor semantics that make the tool unique.

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?

Gives clear usage context ('without needing their tokens', 'more=true means call again for the rest') and the duet channel naming convention. It never explicitly names the alternative (check_monitor with a token) as the case where you should NOT use this, so the when-not is only implied.

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