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

Annotations already declare the read-only, idempotent, non-destructive profile, so the description's job is to add nuance beyond that — and it does: 'never evaluates formulas' and 'presents variations as human review leads' set important expectations about output interpretation. It stops short of describing result structure or finding limits, but with an output schema present that is acceptable.

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 tight sentences: the first defines the check scope, the second front-loads the behavioral caveat about not evaluating formulas. No filler, no repetition of the title.

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?

With annotations, full schema coverage, and an output schema, the description gives an agent enough to select and call correctly, including the crucial caveat that findings are heuristic leads. A brief note on truncation via max_findings would make it fully 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 coverage is 100%, so all three parameters (file_path, sheet_name, max_findings) are fully documented in the schema. The description adds no parameter-level detail such as path resolution behavior or how max_findings truncation affects results, so the baseline 3 applies.

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?

States a specific verb (review) and resource (formula cells in an XLSX sheet) plus exactly what it looks for: cached errors, #REF! text, and relative-pattern variations. The scope is clearly distinct from inspect_workbook, compare_workbooks, and reconcile_totals, though it never names those siblings to make the contrast explicit.

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?

Usage is only implied — an agent can infer this is the tool for auditing formula health, but there is no explicit when-to-use statement, no prerequisites, and no routing versus inspect_workbook or reconcile_totals.

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?

Annotations already declare readOnly/idempotent/non-destructive, yet the description still adds real behavioral detail: duplicate or blank keys are surfaced, keys are never returned, and changed values are suppressed unless include_values is true. These are output-shaping traits the annotations do not cover, though it says nothing about ordering, path resolution errors, or limits beyond the schema's max_reported_changes.

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 short clauses, zero filler, and the core operation is front-loaded ahead of the caveats about keys and changed values. Every sentence carries distinct information.

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?

With an output schema present, return-value explanation is unnecessary, and the description covers the important behavioral caveats (key suppression, duplicate/blank key reporting, include_values default). Minor gap: no mention of path/root prerequisites or failure modes for mismatched schemas, which for a 7-parameter tool would round it out.

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 would be 3; the description earns an extra point by explaining the consequence of include_values (changed cell values excluded by default) and confirming keys are never returned. It still does not clarify how key_columns are matched or what happens when multiple key columns are supplied.

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 opens with a specific verb and resource ('Compare two CSV/XLSX tables') plus the mechanism ('using explicit key columns'), so an agent can immediately tell it apart from inspect_workbook or reconcile_totals. It never names a sibling explicitly, which keeps it just below a 5.

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?

Usage is implied by 'using explicit key columns' and the schema note that keys come from inspect_workbook, suggesting inspect first, compare after. However there is no explicit when-to-use/when-not guidance or statement of which sibling to prefer for alternative tasks such as total reconciliation.

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?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world scope, so the safety profile is covered. The description adds genuine value beyond that: it confirms the operation is confined to KINGWORKBOOK_ROOT and, importantly, that no cell values are returned — a behavioral trait an agent cannot infer from annotations or schema.

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, zero filler. The read-only nature and the root constraint are front-loaded, and the return-field list is compressed into a single clause. Nothing repeats the title or the schema.

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 one-parameter read tool with full annotation coverage and an output schema, the description supplies everything needed to call it correctly: supported formats, path root, read-only semantics, and the fact that values are withheld. Return-value details are left to the output schema, which is the right division of labor.

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 single parameter has 100% schema description coverage with an example ("reports/monthly.xlsx"), so the schema does the heavy lifting. The description only reinforces the KINGWORKBOOK_ROOT anchoring and adds no format, path-resolution, or error semantics beyond it — baseline 3 applies.

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?

States a specific verb and scope ("Read-only profile of a CSV or XLSX file inside KINGWORKBOOK_ROOT") and enumerates exactly what it returns: sheet names, headers, row counts, blank counts, types, formula counts. It is clearly distinct from compare_workbooks and reconcile_totals, though the formula-count return slightly overlaps check_formula_integrity without the description drawing that boundary.

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?

Usage is only implied: "read-only profile ... without cell values" suggests using this for metadata reconnaissance rather than data extraction, and the root-scoped path suggests it must run before other workbook tools. No sentence explicitly says when to choose this over check_formula_integrity or compare_workbooks, and no prerequisites or exclusions are named.

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?

Annotations already declare readOnly, idempotent, non-destructive; the description adds substantive behavior beyond them: formulas are not evaluated, and only usable cached results are labeled and counted. That caveat materially affects how an agent interprets a mismatch, which is exactly the value beyond structured fields.

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 tight sentences: the core operation first, the caveat second. No filler and nothing important buried.

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?

An output schema exists, so return-value explanation is not needed, and annotations cover safety. The description supplies the key caveat about cached vs. formula values; only minor items (e.g., behavior when the column is missing or non-numeric) are left implicit.

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% and every parameter is documented in the schema, including the tolerance default and decimal-string format. The description only echoes the concepts of control total and tolerance without adding format or edge-case guidance, so baseline 3 applies.

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?

States a specific verb chain and resource: sum a selected column and compare against a supplied control total within a tolerance. An agent can distinguish this from compare_workbooks or check_formula_integrity, though it doesn't explicitly name those siblings.

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 the use case (verifying a column total against an expected value) but gives no explicit when-to-use/when-not guidance or routing versus the sibling integrity/compare tools. The 'formulas are not calculated' clause hints at a limitation rather than selecting among alternatives.

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