list_contacts

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

Annotations already mark the tool as read-only, non-destructive, idempotent, and open-world. The description adds critical behavioral details: strict-fail on tamper with specific error types, unsigned in-memory entry merging, demo mode override, and per-(label, chain) conflict resolution. No contradiction with annotations.

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 front-loaded with the primary purpose, then adds important details about tamper handling, unsigned entries, and demo mode. While somewhat dense, each sentence provides value. Minor redundancy in discussing 'unsigned: true' flag, but overall efficient.

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 no output schema, the description fully explains the return format (fields like label, addresses, notes, addedAt, unsigned flag). It covers error conditions, edge cases (unsigned entries, demo mode), and parameter semantics. For a read tool with two optional parameters, this is comprehensively complete.

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 100% schema coverage, the description adds meaning beyond the schema: it explains that omitting 'chain' returns all chains, and using 'label' performs a single-record lookup. This clarifies the default behavior and use case for each parameter.

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 that the tool returns a 'joined per-label view across chains' with specific fields (label, addresses, notes, addedAt, unsigned flag). This differentiates it from sibling tools like 'verify_contacts' (which only verifies) and 'add_contact' (which modifies). The verb 'Return' and the resource 'per-label view' make the purpose specific and unambiguous.

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 explains when to use the optional 'chain' and 'label' parameters: filter by chain or single record search. It also mentions the strict-fail behavior on tamper, guiding agents to surface errors. However, it does not explicitly state when not to use this tool or provide alternatives, though the sibling list implies other contact tools exist.

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