consolidate

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

No annotations are provided, so the description carries the full burden. It does disclose the critical behavior that merging requires confirm=true and that without confirm it only returns candidates, which is a safety-relevant detail. However, it omits what 'merge' actually does (e.g., whether duplicates are deleted, if the operation is reversible). This is an important gap for a potentially destructive action.

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 concise and well-structured: it starts with the core purpose, then gives a usage condition, then describes the default return behavior, and finally the confirmation flag. Each sentence serves a distinct function with no redundancy or fluff.

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 no output schema and no annotations, the description should explain the return value more precisely. It says 'Returns groups of similar captures,' but does not describe the structure of those groups or what happens after a merge. The tool's complexity is moderate, and the description conveys the overall workflow, but missing side-effect details leave the agent uncertain about consequences.

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 input schema provides 100% coverage of the three parameters, so the baseline is 3. The description adds a bit of context for confirm ('Set confirm=true to merge them') but does not meaningfully elaborate on threshold or session_key beyond their schema descriptions. Overall, the description adds minimal value 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 clearly states the tool's purpose: 'Find and merge duplicate or near-duplicate memories.' It uses a specific verb (find and merge) and resource (memories), and gives a concrete example ('same decision captured twice'). This distinguishes it from sibling tools like recall or search, which are for retrieval rather than consolidation.

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?

Explicitly tells the agent when to use the tool: 'Use this when you suspect redundant captures.' It also explains the two-step process: without confirm it returns candidates, with confirm it merges. However, it does not mention when not to use it or provide alternatives, so it falls slightly short of a full 5.

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