mcp_engram_apply_capacity_hot_compress

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

With no annotations, the description carries the full burden of behavioral disclosure. It clearly states the operation is non-deletive ('residency demote only'), lists protected path prefixes, and recommends dry-run first. It does not discuss reversibility or post-run effects, but this is strong transparency for the given context.

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 information-dense and front-loaded with the purpose. Each sentence adds relevant detail: trigger conditions, behavior, protections, and defaults. The protected-prefix list is long but necessary for safety, and there is no filler.

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 2-parameter tool with a detailed schema and no output schema, the description provides trigger conditions, behavioral guarantees, protected namespaces, and defaults. It does not specify the normal return value for non-dry-run calls, but overall it gives enough context for an agent to use it appropriately.

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 already provides rich descriptions for both parameters, including defaults and clamping ('default 64, clamped 1..500') and dry_run behavior. The tool description mostly repeats this information, adding only the HOT_SET_SOFT target and the dry-run preference, so it adds little 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 the exact operation ('unmark non-protected hot residency toward HOT_SET_SOFT (1k)') and identifies it as a capacity/NREM/hot compress path. It distinguishes from deletion by stating 'Does NOT delete blocks — residency demote only' and lists protected prefixes, making it clear what this tool does versus related tools.

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?

Explicit trigger conditions are provided ('when soft_elevated_hot_set or elevated_hot_set'), along with practical guidance to 'Prefer dry_run=true first' and references to 'compress_path.suggested + nrem_candidate_count' as signals for when to call. However, it does not name alternative tools or explicitly state when not to use this tool.

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