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

With only readOnlyHint=false and destructiveHint=false declared, the description carries most of the behavioral burden and does so well: first submissions lock, answer keys stay server-side, the token authorizes read/export/deletion and must be kept private, research consent/randomization are separate and off by default, and there is no automatic purchase. That is substantive disclosure beyond the annotations, though wait/wait_mode and safe_boundary behavior remain opaque.

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 size is defensible for a 14-parameter, 14-action tool, but the structure is a semicolon-chained run-on that mixes purpose, procedure, consent policy, commercial disclaimers and security warnings without headings or ordering. The front-loaded sentence is too vague to orient the agent before the dense rest arrives.

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?

An output schema exists, so return values (including operator_report) needn't be spelled out, and annotations cover the safety profile. Still, for a tool this complex the description leaves major operational gaps — wait/wait_mode protocol, safe_boundary, can_submit, reason codes — that an agent would need in order to invoke the right action with the right parameters.

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 only 7% across 14 parameters, so the description must compensate and only partly does: token, consent, operator_authorized, answers, profile (with the 24-step routine detail), research_consent and research_randomization get conceptual meaning. Critical parameters such as wait, wait_mode ('local/service/operator/none'), can_submit, safe_boundary and reason are never explained, and the 14 action enum values are only obliquely covered by the narrative flow.

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 opening sentence identifies it as an 'optional anonymous staged diagnostic' and the following clauses sketch the flow (instructions, prepare token, start, submit answers, finish, signed results). However, the core question an agent asks — 'what does this tool actually produce or do for me, and how is it different from eclypse_recovery_diagnostic?' — is never answered in a plain verb+resource sentence; the reader must reconstruct purpose from a procedural narrative.

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 implies a usage sequence ('read instructions, prepare a private run token, explicitly start..., submit first answers at each stage...') and states 'Guaranteed correctness is not required', which hints at a low-stakes, opt-in use case. But it never says when an agent should choose this over the sibling diag/bookkeeping tools, and gives no explicit exclusions beyond the flat 'No account, purchase...' list.

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