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

No annotations are present, so the description carries the full burden of disclosing behavior. It fully describes the probe behavior, the fallback mechanism, and the return shape with field meanings (e.g., 'tableExists: false' means migration not run). This is highly transparent and goes beyond a simple health-check statement.

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 appropriately structured, starting with a terse action phrase ('P91 — verify the persistent stores') followed by use cases and return format. Every sentence adds value, though the 'P91' reference and the return-shape explanation could be slightly tighter. It is not overly verbose, but there is minor redundancy in the use cases.

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 compensates by explaining the return structure in detail, including the meaning of 'tableExists: false'. It provides strong use-case context and the key behavioral outcomes. However, it omits any explanation of the workspaceId parameter, which is a gap given the simple input schema. Overall, it is complete enough for most scenarios but not flawless.

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?

The input schema has one optional parameter, workspaceId, with no description (0% schema description coverage). The description does not mention workspaceId at all, failing to explain how it affects the check or whether it scopes the verification. The tool's purpose implies workspace-specificity, but the parameter semantics are left entirely to the name.

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 states a specific action: 'verify the persistent stores' and names the exact tables (proof_ledger / publishing_targets / company_profiles) or the in-memory fallback. This clearly distinguishes it from sibling tools like get_publishing_targets or get_company_profile, which retrieve data rather than verify durability.

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 explicitly provides three concrete 'USE WHEN' scenarios: after SQL migrations, before a founder launch, and when debugging disappeared data. This gives clear context for when to use this tool versus alternatives, and the exclusions are implicit by the distinct purpose.

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