Bilig WorkPaper

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds a crucial behavioral nuance: 'Does not write files by itself', indicating the agent must handle persistence. This goes beyond the annotation hints and prevents a potential misuse.

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 sentences long, front-loaded with the primary action, and contains zero redundant content. Every phrase contributes to understanding the tool's purpose and a key behavioral caveat.

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 export tool with one optional parameter, an output schema, and strong annotations, the description is complete. It covers the target resource, the use cases, and the non-persistence behavior, leaving no obvious gaps for an agent to invoke it correctly.

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 input schema fully describes the only parameter includeConfig with a clear description and default, achieving 100% coverage. The tool description adds no additional parameter semantics, so the baseline score of 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 explicitly states the verb 'Export' and the resource 'current WorkPaper JSON document', clearly distinguishing it from the sibling cell-level operations. The addition of 'for persistence, review, or handoff' further clarifies the tool's role.

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 context for when to use the tool (obtaining a serialized snapshot for persistence, review, or handoff) and implies it is for the current document. It does not explicitly exclude alternatives, but the sibling tools are so obviously distinct that confusion is unlikely.

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 and destructiveHint, so the description adds value by explaining the display vs. raw distinction and that the result is formatted. It does not detail formatting behavior or edge cases, but for a simple read tool with strong annotations this is sufficient.

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 short sentences pack the purpose and usage guidance with no filler. The key information is front-loaded in the first sentence, and the second sentence clarifies when to choose this tool.

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 2-parameter read tool with rich annotations and an output schema, the description fully covers the tool's purpose, usage context, and distinction from siblings. Nothing essential is missing.

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% with clear descriptions for 'address' and 'sheetName'. The description adds no extra parameter-level detail, so it relies on the schema as is appropriate. Baseline of 3 is warranted.

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 uses a specific verb 'Return' and identifies the resource as 'the formatted display string for one cell.' It clearly distinguishes from siblings by noting it returns what a user would see, not the raw numeric value, differentiating it from read_cell.

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?

It explicitly states when to use the tool ('Use when an agent needs what a user would see') and contrasts it with not wanting the raw numeric value, implying the alternative of read_cell. However, it does not name the alternative or provide explicit when-not-to-use guidance.

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=true, idempotentHint=true, and destructiveHint=false. The description adds useful behavioral context by stating 'Returns metadata only,' which clarifies that no cell values are returned even though it is a read-only operation.

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 concise sentences, front-loaded with the primary action and purpose. Every clause adds value: the discovery intent, the timing cue, and the explicit pointer to value-returning siblings.

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 parameters, an output schema present, and rich annotations, the description provides complete context for an agent to invoke the tool correctly. It covers what the tool returns (metadata) and when to use it, and the sibling list provides additional disambiguation.

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 tool has zero parameters, and the schema is empty, so there is little to document. The description reinforces the metadata-only nature and does not introduce any parameter expectations, matching the baseline for parameterless tools.

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 uses a specific verb ('Discover') and clearly identifies the resource ('sheet names and used dimensions') of a WorkPaper. It explicitly distinguishes this metadata-only listing from the sibling tools that return cell values, such as read_range and read_cell.

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?

It explicitly states when to use the tool: 'before reading or editing a WorkPaper.' It also provides a direct alternative for actual values: 'use read_range or read_cell for values,' making the choice between tools unambiguous.

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=true and destructiveHint=false, so safety is covered. The description adds value by specifying the exact fields returned (calculated value, display text, formula text, etc.), which is useful behavioral context beyond the 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?

The description is concise with two sentences: the first states the core function and outputs, the second provides a practical usage tip. No unnecessary words or redundancy.

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 is straightforward (single cell read) with an output schema present. The description covers the key return content and a common use case. It lacks information on error conditions or edge cases, but these are likely captured in the output schema, so completeness is sufficient.

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% with both parameters (sheetName, address) having descriptions. The description does not add additional parameter semantics beyond the schema, so baseline score of 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 reads a single cell and lists specific outputs (calculated value, display text, formula text, formula diagnostics, serialized content). It distinguishes from siblings like read_range (one cell vs. range) and get_cell_display_value (more than just display value).

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 explicitly recommends using this tool after set_cell_contents to verify readback, providing a clear usage context. It does not explicitly mention alternatives or exclusions, but the use case is well-defined given the sibling tool names.

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=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds valuable context that the tool returns calculated values plus serialized formulas/inputs, revealing the output composition beyond a simple read, and its intended audit role. This exceeds annotation-only information without contradicting it.

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 concise two-sentence structure: the first sentence states core functionality, the second provides usage context and alternative guidance. Every sentence earns its place with zero redundancy.

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 low complexity (2 params, output schema present) and strong annotations, the description covers the what, when, why, and alternative. It also clarifies the output involves formulas/inputs and audit usage, making it complete for an agent to select and invoke correctly.

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% for both parameters, with descriptions for 'range' and 'sheetName'. The tool description does not add new details about parameter syntax or behavior beyond the schema, so the baseline of 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 reads calculated values plus serialized formulas/inputs for an A1 range, using a specific verb and resource. It explicitly distinguishes itself from the sibling read_cell tool by noting the latter is for a single address, leaving no ambiguity about scope.

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?

It provides an explicit use case ('audit readback after edits') and directs users to the alternative read_cell for one-address reads. This gives clear guidance on when to use this tool versus its sibling, which is exemplary.

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?

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=true), the description adds meaningful behavioral details: it recalculates dependents, and persistence is conditional on --writable. This gives the agent a richer picture of side effects without contradicting any 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?

The description is two sentences, front-loaded with the primary action, and every clause earns its place. No filler or repetition of schema/annotation info.

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 output schema exists, return values are not needed. The description covers the key behavioral nuances (one-cell write, in-memory dependency recalculation, persistence conditional) and is sufficient for a tool of this complexity.

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 the baseline is 3. The tool description itself does not address parameters directly; all parameter semantics reside in the schema descriptions, which are already thorough. The description adds no extra parameter-level meaning.

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 uses a specific verb ('Write') and resource ('one cell'), and immediately clarifies the scope ('recalculate dependents in memory only'). This distinguishes it from sibling tools like read_cell and set_cell_contents_and_readback, which have 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?

The description provides clear context: writes are in-memory by default, and the --writable flag is needed to persist to JSON. However, it does not explicitly name alternatives or exclusions (e.g., when to use set_cell_contents_and_readback instead), so it stops short of full guidance.

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 declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true. The description adds valuable behavioral context beyond this: it discloses that the tool recalculates dependents, performs a readback before and after the edit, and returns persistence proof—none of which are captured by the annotations and all of which are useful for an agent to anticipate the tool's effects.

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 sentences, front-loaded with the core purpose, and contains no filler. Every clause adds information: the action, the recalculation step, the readback, the persistence proof, and the intended use case. Highly efficient.

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 presence of an output schema (so return values are specified}, and full schema coverage for parameters, the description is complete. It covers what the tool does, why to use it, and important behavioral side effects (recalculation, persistence proof), leaving no critical gaps.

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 thoroughly documents all 5 parameters. The description itself does not add additional parameter-level detail; however, the schema's own descriptions are comprehensive, so the baseline score of 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's function with a specific verb ('write'), resource ('cell'), and unique capability ('recalculate dependents', 'read a dependent range', 'return persistence proof'). It distinguishes itself from the sibling 'set_cell_contents' by explicitly combining write with readback in the same call.

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 gives explicit usage context: 'Use this for stateless MCP clients such as hosted Open WebUI integrations.' It implies the alternative (set_cell_contents) is for stateful clients, though it does not name alternatives explicitly or state when not to use it.

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=true, idempotentHint=true, and destructiveHint=false, establishing the safety profile. The description adds the critical limitation 'This checks syntax only,' clarifying that no evaluation or computation occurs, which is valuable beyond the 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?

The description is two sentences: the first states the primary purpose, the second clarifies the syntax-only scope and points to an alternative for evaluation. Every sentence serves a distinct purpose with no redundancy.

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 validator with rich annotations and an output schema, the description covers what the tool does, when to use it, and what it doesn't do. No critical missing information for an agent to select and invoke it correctly.

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 is fully specified in the schema with type, required, and a detailed description including a leading '=' example. The description doesn't need to add parameter details; schema coverage is 100%, matching the baseline 3.

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 'Validate formula syntax with the WorkPaper parser before writing it to a cell,' specifying the verb (validate), resource (formula syntax with WorkPaper parser), and context (before writing). This distinguishes it from sibling tools that read or write cell contents.

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?

It explicitly says to use this tool before writing a formula to a cell and names the alternative 'use set_cell_contents plus readback to evaluate' for evaluation cases. This gives clear when-to-use and when-not-to-use guidance, outscoring typical sibling differentiation.

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