check_provenance

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It says the tool 'shows where the data came from and when sources were last checked,' which is some behavioral context, but it doesn't disclose what happens if the path doesn't exist, whether it's read-only (implied but not stated), how freshness is measured, or what the output structure looks like. For a read-info tool without annotations, this is a meaningful gap.

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 a single, efficient sentence that fits all relevant information in one breath. It states the verb, resource, and the two key outputs (data origin and last-check timestamps) with zero wasted words. Well-structured and front-loaded.

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 a simple one-parameter lookup tool with full schema coverage and no output schema, the description is mostly adequate. The main gap is behavioral — the tool doesn't explain failure modes or whether it's safe/read-only, which matters given the complete absence of annotations. It's a competent description but doesn't fully round out the usage story for an agent.

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 description coverage is 100%, with the single data_path parameter documenting its format and providing three concrete examples ('pages.home', 'workflows.clock_in', etc.). The description's phrase 'where the data came from and when sources were last checked' slightly enriches understanding of what the parameter's lookup will return, but the heavy lifting is done by the schema. Baseline 3 is appropriate.

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 the tool gets provenance info for a data path and elaborates on what that means ('shows where the data came from and when sources were last checked'). The verb 'Get' plus resource 'provenance info for a data path' is specific and action-oriented. It doesn't explicitly distinguish from siblings by name, but the concept of provenance is unique enough among tools like get_table_schema, get_field, and get_page that differentiation is reasonably clear.

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 provides no guidance on when to use this tool versus alternatives. It doesn't address when provenance matters (e.g., before trusting data, after data updates, for auditing changes) or when a sibling tool like get_field or get_table_schema would be more appropriate. The concept of provenance is implied to be for tracing data origins, but no explicit context or exclusions are given.

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