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

With no annotations, the description carries the full behavioral burden and does so richly: it names the source lens, the four recorded kinds plus the derived toolset_change (and the fields left null for it), the meaning of truncated and skipped, and the failure contract (200 with available:false and a reason, never an empty list passed off as clean). It even discloses the 5-minute cache and its X-Changes-Cache header plus the fact that unavailable responses are never cached.

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 core definition, then a scannable 'when to use' list, then the finer response semantics. It is longer than average, and the paragraph on lens/kinds mixes input semantics with output detail, but every sentence carries information and nothing is filler.

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 must explain return values — and it does: truncated, skipped, the available/reason failure shape, and cache behavior. Combined with the input-schema documentation, an agent has everything needed to call and interpret this tool correctly.

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 already 100%, so the baseline is 3, but the description adds real meaning beyond the schema: it explains that rows come from receipts with lens `config`, enumerates the kinds including the derived toolset_change, and clarifies that truncated is true when more rows exist than limit. That enriches the kind and limit parameters rather than merely restating them.

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: reads back the change ledger of what TunnelMind itself changed in a window, newest first, as an Ed25519-signed document. The scope phrase 'what TunnelMind itself changed' separates it in spirit from external-history tools like get_website_history or get_tool_registry, but no sibling is named explicitly, so it falls just short of a 5.

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?

Provides an explicit 'Use this tool when:' block with two concrete triggers (needing a signed record of changes; checking whether a relied-upon tool or price moved). Covers when-to-use clearly, but offers no when-not-to-use guidance or named alternative tools for adjacent needs.

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