gc_directive

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 usefully discloses that directives are 'injected into agent context automatically', that remove is a 'hard delete', deactivate is 'soft' with later reactivation, and that confirm:true is required for pinned removals. This is meaningful behavioral context that goes beyond the enum values in the schema.

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 vocabulary named first and the action enumeration efficiently packed into one sentence. It's slightly dense — the action list is long and could benefit from being formatted as bullets — but every sentence carries meaningful content with 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 9-parameter tool with 100% schema coverage and no output schema, the description covers the action semantics, scope behavior, persistence vocabulary, and confirmation requirements well. It could add more about what 'inject' returns or how list results are formatted, but given the schema already documents every parameter, the description is reasonably complete.

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 baseline is 3. The description adds meaning beyond the schema by tying parameters to actions (id for remove/deactivate/reactivate, content for add, expires_at for @until, query for inject, confirm for pinned). This cross-referencing between actions and the parameters that apply to them adds genuine value over the flat schema descriptions.

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 manages behavioral directives using a specific vocabulary (@always/@never/@stop/@pin/@until). It names the exact actions available and their semantics. The verb 'manage' plus the explicit vocabulary and scope ('scoped to specific agents or global') makes the purpose specific and effectively distinguishes it from sibling memory tools like gc_recall and gc_retain.

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 enumerates all six actions with one-line definitions, giving clear context for when to use each sub-operation. However, it doesn't explicitly state when to prefer gc_control or gc_hindsight over this tool for related directive/behavior tasks, nor does it name alternative tools explicitly. The action list is a strong usage guide but lacks cross-tool exclusions.

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