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

Annotations already declare readOnly, non-destructive, and closed-world, so the safety profile is covered. The description adds real value beyond that: it discloses multi-match behavior on ambiguous names and clarifies that 'unscored' means never scored rather than zero — a semantic trap it proactively disarms. It stops short of describing no-match behavior or the response shape.

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?

Three short sentences, front-loaded with the core result and the possible values, then ambiguity behavior, then the 'unscored' caveat. Every clause carries information an agent would otherwise get wrong; nothing is padding.

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 3-parameter read tool with full schema coverage and no output schema, the description covers what is returned (strength tier plus last interaction) and two key edge cases. Only the no-match/empty-result case is left unstated, a minor gap against a tool of this simplicity.

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 input schema already explains 'name', 'person', and 'project' fully — baseline 3 applies. The description reinforces that the lookup takes exactly one contact name and tolerates ambiguity, but adds nothing about the run-as 'person' or workspace 'project' parameters 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?

States a specific verb and resource — report the tie strength between a member and one named contact — and enumerates the possible outputs (none, light, moderate, strong) plus the last-interaction timestamp. It does not distinguish itself from adjacent siblings such as connections_contacts_followup_scorecard, connections_contacts_recent_interactions, or connections_contacts_gone_quiet, so an agent must infer the boundary.

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?

There is no explicit when-to-use or when-not-to-use guidance and no sibling is named as an alternative. The only directional signals are behavioral ('returns every match when the name is ambiguous') rather than selection guidance, so the agent must guess why it would pick this over the other relationship-scoring tools.

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