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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety profile is covered. The description still adds real workflow context: results are review candidates and no invoice is deleted as a side effect, which prevents an agent from assuming the call triggers any cleanup.

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 short sentences, zero filler, with the resource stated first and the non-destructive caveat second. Nothing repeats the title or the annotations verbatim without adding meaning.

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 parameterless read tool with no output schema, the description conveys what comes back (groups plus their reasons) and the safety posture. It stops short of hinting at result shape or how to proceed with a group, which is a minor gap given the rich sibling set.

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 schema has a single required 'input' object of type Empty with no properties, so there is effectively nothing to disambiguate. Baseline 4 applies; the description correctly implies a no-argument listing call.

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 ('Read') and resource ('possible duplicate groups and their reasons'), which is far more informative than the bare tool name. It implicitly separates itself from mutating siblings like dismiss_duplicate_group, though it never names them.

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?

'These are candidates for human review' implies the usage context (surfacing duplicates for a person to judge), but there is no explicit when-to-call trigger and no pointer to the sibling that resolves a group once reviewed.

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