verify

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

Annotations declare readOnlyHint=false and destructiveHint=true for the whole tool; the description usefully splits that into per-action read/write labels, which the annotations cannot express. However it never explains the destructive consequences (e.g., source overwriting a prior source, mark mutating a record), so the disclosed safety profile is thinner than the destructiveHint implies.

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?

Action-by-action ordering is well front-loaded and every clause carries information. The opening 'Keep facts current' is the only low-value sentence, and it costs little.

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?

For an 8-parameter, three-mode tool with no output schema, the description covers action semantics but omits what stale actually returns, the role of limit/model, and what happens to previously stored sources on overwrite. Adequate to invoke, incomplete for confident use.

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 38%, so the description carries the burden, and it does: it binds record_type+record_id to mark, maps source to its three enum values, and ties project to writes. It still never explains 'limit' (default 20) or the 'model' parameter, leaving some gap.

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 name 'verify' is generic, but the description compensates by decomposing the tool into three explicit modes (stale read, mark write, source write) with concrete resources (paths, ports, hosts, URLs, config). It also distinguishes itself from the sibling log_change by routing changed facts elsewhere.

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?

Each action states its condition: stale for facts untouched 60+ days, mark once you have confirmed a record still holds, source to record provenance. The closing line 'If a fact changed, log the change instead' is an explicit alternative-path rule, though no explicit 'when not to use' beyond that.

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