sage_directory

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

With no annotations provided, the description fully discloses the tool's behavior. It states the local scope performs one metadata-only database read with no federation probes, and that scope=all adds live-revalidated federated contacts. It further clarifies this is authorization metadata, never online presence or read evidence, and notes that older peers are omitted in an incomplete federated view—providing rich behavioral context beyond structured fields.

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 four sentences, each with a distinct and necessary purpose: stating the core function, explaining scope behavior, listing output fields, and clarifying constraints/caveats. It is front-loaded with the primary purpose and contains no redundant or wasteful phrasing.

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?

The description thoroughly covers inputs (scope semantics), outputs (field list), and important caveats (incomplete federated view, authorization metadata). With schema fully describing the parameters, the combination is sufficient for an agent to invoke the tool correctly and interpret results, even without an output schema.

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 covers 100% of parameters with descriptions for both scope and peer_cursor. The description adds practical semantics by explaining what each scope value does: local performs a metadata-only read with no federation probes, while all explicitly requests the local/federated union. This goes beyond the schema's enum 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 opens with 'List recipients this signed caller is currently authorized to address,' clearly stating the verb (list), resource (recipients), and scope (authorized, local/federated). It distinguishes from sibling tools like sage_find_agent by emphasizing authorization and provenance, even without naming alternatives explicitly.

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 provides clear context for when to use the tool: to enumerate currently authorized recipients. It explains the default local scope versus explicitly requesting scope=all for federated contacts. However, it does not explicitly state exclusions or mention alternative sibling tools for similar operations.

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