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

Annotations already provide readOnlyHint=true and destructiveHint=false, so the description only needs to add behavioral context beyond that. It adds 'presigns' and 'multiple...in one call,' which conveys a batch operation that produces signed URLs rather than raw downloads. However, it does not disclose what happens when agreementIds is omitted or whether the returned data is a list of URLs or something else, and the term 'presigns' is technical enough that an agent might need more context.

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 one short sentence, concise and free of filler. It states the core act, object, and batch nature without redundant phrases, making it easy to scan and understand.

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 has two parameters (one nested required, one nested optional array) and a batch, the description is too sparse. It fails to mention that agreementIds is optional, what happens if omitted, whether it presigns all agreements by default, or that it returns a URL list. The annotations cover read-only behavior and output schema may cover the response format, but the description lacks critical usage details for an agent to call it correctly without guessing.

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 schema description coverage is only 50% and the existing schema descriptions are minimal ('UUID value wrapper'). The description fails to explain what companyId or agreementIds actually mean, aside from implying agreementIds relate to SAFE agreements. It doesn't clarify that companyId is required or how agreementIds is optional and capped at 25, leaving the agent to guess about parameter roles.

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 the specific action ('presigns') and the resource ('multiple SAFE agreement PDFs') in one call, which clearly differentiates it from single-PDF siblings like cap_table_get_cap_table_agreement_pdf_url or cap_table_generate_cap_table_agreement_pdf. However, it could be more explicit about 'download' and would benefit from naming the intended alternative when only one PDF is needed.

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?

There is no explicit guidance about when to use this tool versus alternatives. The description implies a batch use case via 'multiple...in one call,' but it never names sibling tools or states exclusions like 'use this when you need more than one PDF; otherwise use cap_table_get_cap_table_agreement_pdf_url.' This leaves the decision of when to choose this tool to inference.

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