identity

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

Adds substantial context beyond the annotations: it explains the side effect that justifies readOnlyHint=false ('Not a plain read… persists a new agent and reports on that one, marked caller_proven=false'), warns that a cosmetic name never looks an agent up, and clarifies continuity_token is per-process proof whose cross-process use 're-opens silent resurrection'. This is exactly the non-obvious behavior an agent needs. No contradiction with the provided hints.

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?

Purpose is front-loaded in the first sentence, and nearly every clause carries distinct behavioral information. It is a dense single block, though, with compressed jargon ('silent resurrection', 'co-located binding') that costs readability for an 8-parameter dual-mode tool.

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 complex identity tool with 8 optional params and no output schema, the description covers the hard parts — minting gate, cosmetic vs. identity fields, ownership-proof token, and a hint at the reported marker (caller_proven=false). It omits guidance on resume/model_type/agent_uuid and any return-shape detail, but those are largely covered by the 100%-covered schema.

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 baseline is 3, but the description adds cross-parameter interaction semantics the schema does not carry: the gating rule keyed on presence/absence of proof arguments, and the note that name= is cosmetic and thread-safe guidance ('Thread uuid across tools, not this'). That is genuine value above 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 dual purpose: 'Resolve which agent this MCP session is bound to, or set a cosmetic display name.' The verb+resource pair is concrete and the two modes are distinguishable. Sibling differentiation is weak, though — it points to 'onboard(force_new=true)', which is not among the listed siblings, and never contrasts with the actual sibling 'start_session'.

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 real branching guidance: a call with no proof argument is gated to a fresh mint, a call with only a cosmetic name= skips the gate and can infer a co-located binding, and pass client_session_id to get your own back. It routes to an alternative ('onboard') for a fresh process. It stops short of an explicit 'use this instead of X when…' rule against the real sibling set.

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