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

Annotations already cover readOnly/non-destructive/closed-world, and the description adds real value on top: no sign-in or auth is required, the data is rebuilt from current public profiles (so it may differ from a saved version and reflects live data), and it is not a commitment or grant of permission. That last disclaimer is genuinely useful behavioral context an agent would otherwise not have.

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?

Two tight sentences, zero filler, with the core action and its derivation source front-loaded before the disclaimer. Every clause carries distinct information.

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?

There is no output schema, so the description must carry the burden of explaining what a 'connection preview' returns — it does not describe the payload or whether the preview can be incomplete or stale. Sufficient to understand the tool's nature and access model, but not sufficient to know what comes back.

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 0% — the single required proposalId has machine constraints (uuid format, regex pattern) but no textual explanation, and the description never mentions the parameter at all. With low coverage the description is expected to compensate, but it adds nothing about what a proposalId identifies, where it comes from, or what happens with an invalid or expired one.

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 ('Read a connection suggestion') and clarifies it is rebuilt from current public profiles rather than the saved plan. It distinguishes itself from an unnamed alternative concept (the private saved plan) but does not name or differentiate against the listed siblings such as get_person_card or preview_profile, so an agent still has to infer which read tool to pick.

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?

Usage is implied — reading an anonymous, shareable preview by proposalId without signing in — but there is no explicit 'use this when' statement and no routing to alternatives among the nine siblings. The negative framing ('not the private saved plan') hints at when this is the wrong tool without ever saying when it is the right one.

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