Rotate Agent Key

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

With readOnlyHint=true and destructiveHint=false already asserted, the description supplies the missing behavioral context that reconciles them: 'nothing is persisted', the DID document is not returned, copy counts out to a text summary, the full new private key is redacted under MCP_TRANSPORT=sse or MCP_REMOTE=1, and a non-empty delegation_ids_to_revoke is refused before any key is generated. That pre-empts the most likely operational surprises (remote redaction, hard refusal) far beyond what the annotations 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?

The purpose and mode semantics are front-loaded, and every subsequent clause covers a distinct, genuinely useful fact (returned fields, redaction, non-persistence, refusal path). It is denser and longer than most definitions, but the length is earned by the number of edge cases it discloses.

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 correctly carries the entire return-value burden and enumerates the summary contents (rotation state, key prefixes, DID, log entry count, activation time) plus the redaction and refusal behaviors. Nothing an agent needs to call this mutation-shaped computation safely appears to be missing.

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 coverage is 80% and the enum on 'mode' is self-documenting, so the baseline is already 3; the description adds meaning on top by spelling out what planned vs emergency actually do and by restating the delegation_ids_to_revoke refusal rule in prose. It leaves activation_delay_hours and agent_name to the schema, so it is additive but not exhaustive.

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 ('Rotate an agent's Ed25519 key') plus the two operational modes, immediately distinguishing it from generate_keys and the read-only rotation helpers (verify_rotation_chain, is_key_active). An agent knows exactly what the call performs and what it produces 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 real when-to-use context by contrasting 'Planned mode: configurable overlap (default 24h)' against 'Emergency mode: immediate old-key retirement', so an agent can pick a mode. It does not, however, name the sibling alternative (e.g. generate_keys for a fresh identity) or state when not to rotate at all, so it stops short of full routing guidance.

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