consolidate

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

With no annotations, the description fully carries the burden of disclosing behavior. It explains that the tool is destructive ('deletes originals') and runs a 'forget-sweep'. It mentions that results are 'protected learning-layer entries' and that dry_run previews without writing. While some terms like 'forget-sweep' are not further explained, the overall destructive nature and side effects are transparent. Score 4 for solid disclosure.

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 two sentences, front-loading the primary action and listing key steps. Every sentence adds value: first defines the operation, second gives usage guidance. No fluff or redundancy. This is a model of concise yet informative description.

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?

Given there is no output schema, the description should explain what happens and what the output looks like. It covers the process (clustering, summarizing, deleting, forget-sweep) and mentions dry_run. However, it omits details on the 'forget-sweep' and what 'protected learning-layer entry' means. For a tool with 3 parameters and no output schema, this is reasonably complete, but leaves minor gaps.

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 67% (2 of 3 params have descriptions). The tool description adds context around 'cold low-importance memories' which helps interpret the min_age_days parameter. It also reinforces dry_run usage. The scope parameter's enum values are not elaborated in the description, but the tool's domain implies session vs all. Overall, the description adds meaningful context beyond the schema, scoring a 4.

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 action: 'Sleep-mode compression. Clusters cold low-importance memories by (entity, layer), summarizes each cluster into a single protected learning-layer entry, deletes originals, and runs a forget-sweep.' It provides a specific verb (compress/cluster/summarize/delete) and resource (memories). This clearly distinguishes it from sibling tools like 'forget' (individual deletion) or 'remember' (saving).

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 explicitly recommends when to use: 'Run at session end or on demand.' It also advises on dry_run usage. However, it does not explicitly state when not to use it or provide alternatives, such as using 'forget' for single-item deletion. The context is clear but lacks exclusionary guidance, scoring a 4.

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