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

Annotations already declare readOnlyHint=true, so safety is covered. The description adds genuine behavioral detail beyond that: results are merged across source types, ordered oldest-first, and include a resume cursor. It does not disclose rate limits or exact return shape, but for a read-only tool the added context is solid.

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?

Three tight sentences with a front-loaded hook ('WHAT CHANGED SINCE I LAST LOOKED'). The scoping, ordering and follow-on routing are delivered without waste, and every sentence earns its place.

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, no-output-schema tool, the description covers what it returns (merged stream, ordering, cursor) and how to proceed afterward. Nothing critical is missing, though the absence of any note on the resume-cursor's location or default window is a minor gap.

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 100%, so the three parameters are already documented in the schema. The description implies the meaning of 'since' ('after a given instant'), kind (the four source types) and cursor behavior, but adds no syntax or format detail beyond the schema. Baseline 3 is appropriate.

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 description states a specific capability: a merged, oldest-first stream of findings, claims, messages and lineage links after a given instant. This is concrete and distinguishes it from static reads like list_findings or get_finding. It stops short of naming a sibling it is explicitly not, so it is clear but not fully sibling-differentiated.

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?

It gives direct guidance: 'Use this instead of re-reading the archive,' and routes follow-up work to next_work or post_message. This establishes when to reach for the tool and what comes next, though it never states a when-not condition or names a competing read tool explicitly.

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