Tuper Sheets formulas

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

Annotations cover the safety profile (readOnly, idempotent, closed-world), so the description's real contribution is the order-dependence of the cleanups array and the fact that per-cleanup replacement counts are returned — meaningful behavior not in the structured fields. It does not say what happens if text exceeds 50,000 characters or if a cleanup name is unknown, which keeps it short of 5.

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, front-loaded with the action and scope, then the ordering rule and return shape. Slight redundancy in re-listing enum values already present in the schema keeps it from a 5.

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 two-parameter, closed-world tool with annotations covering safety and no output schema, the description says enough: inputs, order semantics, size cap, and return value. Only edge-case behavior (oversized text, invalid cleanup) is left unspecified.

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 0%, but the description compensates well: it names all eight enum values, states that order matters ('in the order given'), and restates the 50,000-character cap on the text parameter. The enum ordering semantics are genuinely additive beyond the raw schema.

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 resource ('Run ReplaceKit cleanups on text'), names the scope limit (50,000 characters), and enumerates exactly which cleanups exist. This is unambiguous and clearly distinct from the sibling formula tools, which operate on Google Docs/Sheets rather than raw pasted text.

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 the title ('Clean pasted text') and the description, but there is no explicit when-to-use or when-not-to-use guidance, nor any reference to alternatives. With no overlapping sibling, the omission is low-risk but still a gap.

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 establish that the tool is read-only, idempotent, and not open-world. The description adds meaningful behavioral detail by listing the case shapes it detects (ALL CAPS, Title Case, First letter, lower) and stating that the output is shaped per match. It does not describe edge cases such as mixed casing or empty strings, so it is not fully transparent.

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 two efficient sentences with no filler. The core behavior is front-loaded, and the Google Docs reference adds useful context without distracting from the operation.

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 two-parameter helper, the description covers the operation and case-shape categories. However, because there is no output schema, it should more explicitly state the return shape and behavior when matches vary or are empty; those gaps matter for an agent interpreting 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 description coverage is 0%, so the description must carry the semantic load. It does explain that 'matches' provides the case-shape source for each replacement, which is useful beyond the raw schema types, but it does not clarify array alignment, the 100-item maximum, or how edge-case values affect the output.

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 states a specific transformation: given matched texts and a replacement, return each replacement shaped to the case pattern of its corresponding match. It clearly distinguishes itself from generic text-cleaning or spreadsheet-formula helpers. It does not explicitly contrast with siblings, but no sibling appears to perform the same case-preserving replacement.

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 Google Docs 'Keep the case of each match' reference implies a usage context, namely reproducing that ReplaceKit/Google Docs behavior. However, it does not explicitly say when to call this tool versus doing case adjustment elsewhere, nor does it state exclusions or prerequisites.

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 and closed-world, so the safety profile is covered. The description adds real context beyond that: it states the return value ('the formula and a note'), the 3-condition cap, and that a no-match message wraps the result in IFERROR, which the annotations do not convey.

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 compact sentences with the core capability front-loaded and secondary features (sorting, no-match message, return value) trailing. No filler or 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?

A 9-parameter tool with 56% schema coverage and no output schema needs a bit more from the description. Calling it out as returning 'the formula and a note' is helpful, but five parameters (join, separator, skip_blanks, case_sensitive, cells_are_text) are left entirely to the schema, leaving an agent reason to open the schema for basic behavior.

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 56%. The description meaningfully names the operation families (equals, contains, starts/ends, one of, blank, number and date comparisons) and flags sorting and the no-match message, mapping to the op enum and order/no_match_message params. It says nothing about join, separator, skip_blanks, case_sensitive or cells_are_text, so several parameters remain documented only in the schema.

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 resource: 'Build a FILTER formula that shows the rows of a range matching 1-3 conditions'. The operator families, optional sorting and no-match message make it fully distinguishable from siblings like sheets_rank_formula or sheets_unique_formula, which build different formula types.

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 purpose strongly implies when to use it (you want a FILTER formula over a range), and the 1-3 condition cap sets a boundary. However, there is no explicit when-to-use/when-not wording and no mention of alternatives such as building the formula manually or using another sheet-formula sibling.

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 and closed-world, so the safety profile is covered. The description adds genuine behavioral context beyond that: it explains that output is a formula string whose shape depends on mode, and enumerates the concrete tie-handling outputs (1,2,2,4 vs 1,2,2,3 vs 1,2.5,2.5,4 vs 1,2,3,4), which the agent could not infer from annotations.

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?

A single tight paragraph that front-loads the core purpose and then packs tie examples and mode semantics without filler. Slightly dense as a wall of parenthetical options, but every clause carries 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?

The tool's job is to emit a formula string and the description makes that clear, so the absence of an output schema is not a problem. Range format quirks are left to the schema's own description, which is acceptable, though a note on what the returned string looks like would have closed the last gap.

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?

With 67% schema coverage, the description meaningfully supplements the schema: it defines the semantics of ties with worked sequences, explains what each mode produces, and clarifies that group causes ranks to restart per group. The only gap is direction/separator, which the schema already documents.

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?

Opens with a specific verb+resource: "Build a formula that ranks one column," which is unambiguous and distinct from the sibling filter/unique formula builders. It never explicitly names how it differs from sheets_filter_formula or sheets_unique_formula, so it stops short of the top mark.

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 through the mode explanation ("column fills the whole column from one cell; row is a per-row formula to drag down"), which helps pick a mode but is parameter guidance rather than when-to-use-this-tool guidance. There is no statement of when to choose this over the sibling formula tools or any preconditions on the range.

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 and closed-world, so safety is covered. The description usefully signals that the output is a generated formula rather than computed data, but it does not state what the returned string looks like, whether it must be pasted into a cell, or how locale/separator interacts with the generated syntax.

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?

A single front-loaded sentence that packs the verb, the resource and all five variants with zero filler. Nothing could be removed without losing 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 no output schema and three undocumented parameters, the description leaves real gaps: the return type (formula string), the multi-column restriction noted only in the range schema, and the meaning of order/ignore_case/skip_blanks. Adequate to start, insufficient to invoke confidently across all modes.

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?

At 33% schema coverage, the description partially compensates by giving semantics to the five mode values (list, count, counts, dupes, once). However, order, ignore_case and skip_blanks have no description text anywhere, and the description never mentions sorting, case folding or blank handling at all.

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 resource ("Build a formula for unique values") and enumerates the five output flavors, which an agent can map onto the mode enum. It never names a sibling, so the agent cannot tell from the description alone why this is preferable to sheets_filter_formula or sheets_rank_formula.

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 enumerated variants imply when the tool is appropriate (dedup, frequency counts, duplicate detection), but there is no explicit when-to-use vs when-not, and no routing to the sibling formula builders. An agent must infer the boundary from the variant list.

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