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

Beyond the annotations (destructive/openWorld/non-idempotent), it discloses login requirement, the two-step preview-then-confirm safety flow, the notification sent to the counterparty, and the re-validation of status/visibility/blocking with a no-switch fallback on failure. This is substantive behavioral context the annotations alone do not convey.

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?

A single dense semicolon-delimited block that front-loads the login requirement and requestId. Every clause contributes (workflow, consent rules, side effects, failure handling), though the packed style makes it slightly effortful to parse.

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 destructive 7-parameter mutation with no output schema, it covers the critical gaps: preconditions (login), confirmation protocol, required accept-time inputs, side effects, and failure behavior. It stops short of describing the response shape or what previewHash represents, which would complete it.

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?

With only 29% schema description coverage the description must carry the load, and it does: it explains action roles, the consent/previewHash/preview execution trio, and that accept additionally requires a self-provided contact plus shareContactConsent while decline/cancel take none. It adds real meaning, though the previewHash semantics are only implied rather than defined.

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 title and opening clause state a specific verb (respond/withdraw) plus resource (connection request) and immediately disambiguate the three action roles: recipient accepts/declines, initiator cancels. An agent can tell this apart from siblings like create_connection_request or get_connection_request without opening the schema.

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?

It gives clear conditional guidance: which actor uses accept/decline vs cancel, that the default is a preview, and that execution requires re-issuing the same parameters with previewHash, consent=true and preview=false. It does not name an explicit alternative tool, but the workflow and actor conditions are spelled out well enough to guide selection.

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