InferMap

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

With no annotations, the description carries full burden. It discloses the basic behavior (rename columns, write output) but lacks details on permissions, overwrite behavior, error handling, or side effects. Average transparency.

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?

Single sentence that is efficiently front-loaded with the action. No wasted words. Could be more structured with bullet points, but it is concise and clear.

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 3 required string parameters and no output schema, the description is adequate but incomplete. It doesn't mention return values, output format, or potential errors. For a transformation tool, slightly more detail would be beneficial.

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 100%, so baseline is 3. The tool description adds context about the config parameter (renaming columns) but does not further elaborate on parameter values or constraints beyond what the schema provides.

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 action 'Apply a saved mapping config to a source CSV', specifies the resource (mapping config and source CSV), and details the effect 'renaming columns and writing to output file'. It distinguishes itself from sibling tools like inspect, map, and validate.

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?

No explicit guidance on when to use this tool versus alternatives. The description implies its purpose but does not mention when not to use it or compare to siblings like inspect or validate.

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

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

With no annotations, the description carries the burden of transparency. It explicitly states the tool reads and returns statistical summaries, implying a non-destructive operation. No hidden side effects are mentioned, but the behavior is clear from the description.

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, concise sentence that front-loads the purpose ('Inspect a data source') and lists key outputs. Every word adds value, with no redundancy or unnecessary detail.

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 the absence of an output schema, the description adequately explains what the tool returns (fields, types, sample values, null rates, unique rates, statistics). It does not cover error handling or limits, but for a straightforward inspection tool it is largely complete.

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%, so the schema already describes both parameters ('table' and 'source') adequately. The tool description adds no additional meaning beyond what the schema provides, meeting the baseline for high coverage.

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 specifies the action ('inspect a data source') and lists the exact information returned (fields, types, sample values, null rates, unique rates, statistics). It differentiates from sibling tools (apply, map, validate) which perform transformations or checks rather than exploratory analysis.

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 usage for data exploration and profiling, making it clear when to use this tool. However, it does not explicitly state when not to use it or provide alternatives among siblings, but the context is sufficient for an agent.

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

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

No annotations provided, so description carries full burden. It discloses pipeline type, output (mappings with confidence and reasoning), but does not state side effects, required permissions, or whether it modifies data. Adequate but incomplete.

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?

Two sentences with no wasted words. Front-loaded with action and method, efficiently conveying core purpose and output.

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 6 parameters, no output schema, and no annotations, the description provides sufficient context for selecting the tool. It explains what mapping is done and what is returned, though could benefit from contrasting with siblings or clarifying process boundaries.

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 100%, so baseline is 3. Description adds context ('weighted scorer pipeline') but does not elaborate on parameters beyond what schema already provides, such as format requirements or usage examples.

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?

Description states verb 'map', specific resource 'source columns to target schema', and method 'weighted scorer pipeline with optimal 1:1 assignment'. Clearly distinguishes from siblings (apply, inspect, validate) which serve different purposes.

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?

Implies usage for mapping columns to a schema, but lacks explicit guidance on when to use vs. siblings (e.g., when to inspect or validate). No mention of prerequisites or when not to use.

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

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

With no annotations, the description carries full burden. It discloses key behaviors: validation of column compatibility and reporting of two issue types. However, it does not mention side effects, permissions, error handling, or return format, leaving gaps for an AI agent.

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?

Two sentences, no extraneous information. The first sentence states the purpose, the second adds detail. Efficient 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?

No output schema exists, so description must explain return values. It says 'Reports missing source columns and unmapped required fields' but does not specify the format or structure of the report. Adequate for a simple validation outcome but lacks completeness for an AI agent to fully interpret results.

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 100%, so baseline is 3. The description does not add significant meaning beyond what the parameter names and schema descriptions already provide. It mentions the validation task but no extra semantic detail for the parameters.

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 specifies the verb 'Validate' and the resource 'source file's columns against a mapping config'. It also mentions what it reports (missing columns and unmapped fields), which distinguishes it from sibling tools like 'apply' (executes mapping) and 'inspect' (examines structure).

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?

No explicit guidance on when to use this tool versus alternatives like 'apply' or 'inspect'. The description implies it's a pre-step before applying a mapping, but does not state when not to use it or how it differs from sibling tools.

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