get_relationship_summary

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

No annotations are provided, so the description carries the full burden. It thoroughly explains what the tool returns (contact metrics, staleness flag, commitments), but doesn't disclose whether staleness uses the passed threshold, read-only behavior is implied but not stated, or performance characteristics. It adds reasonable behavioral context but doesn't fully compensate for the lack of annotations.

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 well-organized with a clear header line, a bulleted list of return contents, and a usage recommendation. The bullet list is efficient and front-loads the key purpose. The single usage sentence earns its place. Well structured and scannable without redundancy.

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 an output schema exists (so return format is documented elsewhere) and 100% schema coverage, the description adequately covers the tool's behavior. It lists key output categories and provides usage context. It could mention how staleness interacts with the threshold parameter across invocations, but for a read-only summary tool with good schema support, this 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 schema already documents both parameters (email and stale_threshold_days). The description adds context on staleness (the concept and default threshold reference) but doesn't add meaningful syntax or format details beyond the schema. Baseline 3 is appropriate when the schema handles parameter documentation well.

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 purpose: 'Get comprehensive relationship summary for a person' and enumerates the specific data it returns (last contact date, days since last contact, interaction count, commitments, staleness). This distinct resource+verb clearly separates it from sibling tools like get_person_history and get_meeting_context.

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 ends with explicit when-to-use guidance: 'Use this before meetings to understand your relationship history.' While it doesn't explicitly name alternative tools or when not to use it, sibling tools like get_follow_ups_with_person and get_stale_relationships exist as narrower alternatives, so some exclusion context would strengthen this. The meeting context is clear enough.

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