request_contact

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

With no annotations, the description carries full behavioral burden. It does disclose the core mutation (creates/refreshes an AgentLink, sends an ack_required message), which is genuinely useful. But it omits material side effects visible in the schema: register_if_missing defaults to true (implying this call may auto-register an agent) and registration_token exists — neither is mentioned, nor is any auth or rate-limit context.

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?

Front-loaded with the action and effect, then cleanly sectioned under 'Discovery' and 'Parameters' headings. Slightly padded by restating the discovery resource both in prose and in the to_agent description, but overall well-sized and scannable.

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?

An output schema exists, so return values need no explanation, and the core workflow is covered. But for a 12-parameter mutation tool with zero schema coverage, leaving six parameters — notably register_if_missing and registration_token — undocumented means an agent cannot fully predict the call's side effects, which is a meaningful completeness gap.

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%, so the description must compensate, and it documents only 6 of 12 parameters (project_key, from_agent, to_agent, to_project, reason, ttl_seconds) with useful semantics such as ttl default of 7 days and cross-project intent. It leaves model, format, program, task_description, registration_token, and register_if_missing entirely undocumented, so half the surface — including a behavior-changing flag — has no explanation anywhere.

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+resource ('Request contact approval to message another agent') and immediately describes the concrete effect: 'Creates (or refreshes) a pending AgentLink and sends a small ack_required intro message.' This distinguishes it from siblings like send_message, respond_contact, list_contacts, and set_contact_policy without needing to open any 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?

Gives clear context for use (cross-project coordination, discovering target agents) and points at resource://agents/{project_key} for name discovery. However, it never names an alternative tool or states when NOT to use it — e.g. that respond_contact handles the approval side or send_message handles the post-approval messaging — so the agent must infer the workflow boundary.

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