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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered; the description's domain semantics go beyond that — stage buckets are exclusive (each investor counted once) and 'Raised' equals the wired bucket only, while committed/signed are promised but not received. This is exactly the non-obvious interpretation guidance annotations cannot supply.

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 return contents are front-loaded before the usage guidance, which is the right ordering. The description is on the long side but nearly every clause earns its place by defining the buckets and the raised/committed distinction; the 'Read-only' sentence is redundant with annotations.

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 structure need not be described, yet the description usefully explains what the returned buckets mean and how they combine. It stops short of noting edge cases such as companies or rounds with no investors or an empty result set, which is a minor gap for a nested-output read tool.

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?

There is a single parameter (companyId) with 100% schema description coverage, so the schema carries the parameter burden and the baseline is 3. The description adds nothing about the expected companyId value or scope (e.g., whether it accepts a company the user does not belong to), leaving parameter meaning entirely to 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?

The description names a specific resource (funding rounds with investors attached) and enumerates exactly what is returned: capital per pipeline stage (committed, signed, wired), total raised, and investor count. It distinguishes the output from hand-summing individual investors, though it never names a sibling tool such as cap_table_get_cap_table_round or cap_table_get_list_cap_table_stakeholders, which keeps it short of 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?

It supplies concrete triggering questions ('how is the round going', 'how much have we actually collected') and clarifies when to combine buckets ('add them yourself only when the user asks what is promised in total'). It implies the alternative (summing stakeholders manually) but does not name a specific sibling tool to use instead, so it falls short of explicit when-not guidance.

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