gc_engagement

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states 'Screen-first by default' and 'File output only when target=file|both', which is useful. However, it doesn't disclose key behavioral traits: what the audit entails, whether compute is destructive, what sensitivity changes, or what happens on errors. The action enum partially compensates by implying the range of behaviors, but significant behavioral gaps remain.

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 front-loaded with the core purpose, followed by the default behavior and action list. The two-line format is efficient and scannable. Minor redundancy: the action list is fully mirrored in the schema's enum, so listing it again is somewhat redundant, but it aids quick scanning.

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 fairly complex tool with 15 parameters and 6 actions, no output schema, and no annotations, the description is on the thinner side. It covers the default target, the action set, and the data sources, but doesn't explain the relationship between parameters like k_values/tolerance_minutes/bin_minutes and the sensitivity/audit actions, nor what the audit CSV includes. Given schema coverage of 100%, the description doesn't need to restate params, but should clarify action-specific behaviors for completeness.

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 100%, so the schema already documents all 15 parameters thoroughly. The description adds value by explaining the default target behavior and listing the actions, but doesn't elaborate on parameter semantics beyond the schema. Baseline 3 is appropriate since the schema does the heavy lifting; the description's mention of 'target=file|both' and default tolerances adds modest context.

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 verb ('Reconstruct engaged-attention hours from Timing presence plus project-touch events') and the resource (Timing + project-touch events across tools). It lists the specific actions available. However, it doesn't distinguish itself from siblings like gc_timing or gc_sessions, which could overlap with timing/attention data; the tool's unique value (merging Timing presence with project-touch events) is stated but not contrasted against 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?

The description gives an implicit sense of when to use it (for reconstructing engaged-attention hours and various analysis actions), but provides no explicit when-to-use vs alternatives guidance. The list of actions hints at use cases (compute, audit, sensitivity, etc.), but there's no direction on which sibling tool to use instead when the user just needs raw timing data or session records. Also no prerequisites, default behaviors beyond target/tolerance are partly implied.

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