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

Annotations already declare readOnlyHint=true, so the read-only nature is covered. The description adds substantial behavioral detail beyond annotations: the result is 'token-optimized, never includes the raw binary,' the exact output components are listed, and re-calling with structure_override is described as the correction path for misdetected ledgers.

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?

Three sentences carry a large amount of information with no filler: the first defines the operation and output, the second connects it to its downstream siblings, and the third explains the correction workflow. It is appropriately concise 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?

Given the tool's moderate complexity, the description covers the essential operational context: what it parses, what it returns, how it fits into the broader workflow, and how to recover from misdetection. There is no output schema, so the description's explicit listing of return contents is sufficient. The schema covers sheet_name behavior, completing the picture.

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?

Input schema coverage is 100%, so the schema already fully documents all parameters and nested fields. The description adds pipeline-level context around structure_override (e.g., misdetected 'Débit' column), which is helpful but does not add parameter-level semantics beyond what the schema descriptions already provide.

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 a specific verb and resource: 'Parse an Excel/CSV file uploaded out-of-band via layerz_create_upload_url.' It lists the exact return payload (timeline, suggested_structure, row labels, column headers with samples) and distinguishes this parse step from the sibling pipeline tools like layerz_match_items and layerz_import_branch.

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 clear pipeline context: the agent typically feeds row labels into layerz_match_items and then builds entries[] for layerz_import_branch. It also gives explicit re-call guidance when misdetection occurs, but it does not explicitly state when not to use this tool relative to all alternatives.

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