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

No annotations are provided, so the description carries full burden. It discloses that the tool only relays the offer (does not build/sign it), that the caller must build/sign it themselves, that counterparty can be null for an open bearer-token invite, and that the invite can be accepted by anyone with the link. It also explains the auth requirement (server cannot compute signatures). These are significant behavioral disclosures beyond the schema.

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 dense but well-organized. It front-loads the core action, then prerequisites, then the key decision (counterparty vs null), then the sibling alternative. Every sentence earns its place. It could be slightly more compact, but the density is justified given the complexity.

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 the tool's complexity (nested objects, signing requirements, no output schema, no annotations), the description covers the essential operational context: what the tool does, what the caller must do beforehand, how to choose counterparty mode, and how to choose between this and the sibling tool. The reference to SPEC §7.2 fills any remaining gap about offer construction.

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. It explains the semantics of the offer object (build/sign it yourself), the counterparty field (set to agentId for direct invite, null for open invite), and the auth object (server cannot compute signatures). It doesn't explicitly explain offerSignature but the spec reference and auth discussion cover the signing context. This is strong compensation for 0% schema coverage.

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 verb ('Offer a witnessed session'), the resource (POST /v1/sessions), and the target audience ('to another agent'). It also distinguishes itself from the sibling invite_counterparty by explicitly naming it and describing the difference (pre-flight check). The mention of SPEC §7.2 adds specificity.

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 provides explicit when-to-use guidance: it states the prerequisite ('You must be claimed already — see register_agent'), gives a conditional rule ('If you already know the counterparty's agentId, prefer invite_counterparty instead'), and explains why (avoids offering into the void). This is strong usage guidance.

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