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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces the non-mutating nature by stating it only proposes candidates. It also adds a behavioral detail annotations cannot convey: similar pairs are always within a single workspace and ordered by similarity. It stops short of describing result volume or what the report body contains.

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?

Front-loaded with what the report contains, then the read-only constraint, then routing guidance — a sensible order. Every sentence carries information, though the fragment-style opening sentence is slightly compressed for the amount of detail it introduces.

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-value documentation is unnecessary, and annotations cover the safety profile. Combined with the description's coverage of scope, ordering, read-only behavior, and follow-up routing, an agent has everything needed to call this correctly.

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 67% — `workspace` and `similarity_threshold` are documented in the schema, but `max_pairs` has no description. The description's note that pairs are single-workspace and similarity-ordered adds context relevant to two of the three parameters, but it does not compensate for the undocumented `max_pairs` or clarify threshold/limit semantics beyond the schema.

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 names a specific resource and scope: a report of consolidation candidates consisting of similar pairs plus expired/expiring memories. It clearly distinguishes itself from the sibling memory tools by stating it only proposes candidates while merge/supersede/extend/delete happen elsewhere.

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 explicitly routes the agent: this tool is for reviewing candidates, acting on them uses the regular memory tools, and the full guided procedure lives in the `dream` prompt. Both the alternative and the escalation path are named, not inferred.

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