SheetsData MCP

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

Annotations indicate readOnlyHint=true, destructiveHint=false, and openWorldHint=true, covering safety and scope. The description adds valuable behavioral context beyond annotations: it specifies the tool is 'free, non-blocking — returns immediately,' describes the three possible status outcomes ('ready', 'queued', 'error'), and mentions the 20-part limit, which enhances transparency without contradicting 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 well-structured and front-loaded with key information (purpose, behavior, example). While it includes necessary detailed warnings, some sentences could be more concise (e.g., the list of invalid inputs is repetitive). Overall, it efficiently conveys critical usage rules without excessive verbosity.

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 complexity (batch processing with status tracking), the description is complete: it explains the purpose, usage context, behavioral traits, parameter semantics, and integration with sibling tools like 'read_datasheet' and 'search_parts'. Although there's no output schema, it describes the return statuses adequately, making it sufficient for an agent to use the tool effectively.

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 baseline is 3. The description adds significant semantic value by elaborating on what constitutes valid 'part_numbers': it provides examples of real MPNs (e.g., 'STM32F446RCT6'), lists invalid inputs (bare values, descriptions, designators), and advises using 'search_parts' for BOMs without MPNs. This goes beyond the schema's basic description, justifying a higher score.

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 purpose with specific verbs ('trigger background datasheet extraction') and resources ('multiple parts at once'), distinguishing it from siblings like 'read_datasheet' (which reads already-extracted datasheets) and 'search_parts' (which finds MPNs). It explicitly mentions the non-blocking nature and status return, which differentiates it from synchronous extraction tools.

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 explicit guidance on when to use this tool ('to warm up datasheets for a BOM before calling read_datasheet') and when not to use it (with bare values, descriptions, or designators). It names alternatives like 'search_parts' for finding MPNs and specifies exclusions for passives without MPNs, offering comprehensive usage context.

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