consolidate

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

Since no annotations are provided, the description carries the full transparency burden. It explicitly states 'READ-ONLY' and 'Nothing is modified', which is critical for a tool that could be mistaken for a mutating operation. It also discloses the eventual fate of sources after merge_memories: 'marked superseded (never deleted, always recoverable)', giving recovery guarantees without needing annotations.

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?

The description is compact and well-structured: a one-line purpose with the read-only caveat, a short behavioral explanation, a clear workflow sentence, and an Args list. Every sentence adds value—no filler or repetition of schema defaults. The front-loading of 'READ-ONLY' is strategically effective.

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 tool with 3 optional parameters and no annotations, the description covers purpose, usage workflow, behavioral guarantees, and parameter semantics. An output schema exists, so the absence of return-value details is acceptable. It provides everything an agent needs to decide when to call it and what to expect.

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 description coverage is 0%, so the description is the sole source of parameter meaning. It explains all three parameters clearly: 'project' scopes to a project or None for whole brain, 'threshold' defines the cosine similarity cutoff for redundancy, and 'max_groups' caps the number of returned groups. This goes far beyond the bare schema titles.

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 opens with a specific verb and resource: 'Propose groups of redundant/overlapping memories to merge.' It clearly distinguishes from siblings like merge_memories by emphasizing the read-only proposal nature. The parenthetical '(READ-ONLY)' and the explanation that nothing is modified further solidify the purpose.

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 description provides explicit when-to-use and when-to-then-use-alternative guidance: 'review the groups, write a synthesis yourself, then call merge_memories(...)'. This tells the agent exactly how to proceed after calling this tool, effectively naming merge_memories as the complementary next step. It also clarifies that this tool is for proposing, not executing merges.

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