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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the description's extra value is the payload behavior it discloses: valuation marks and operating metrics are returned newest-first, and runway is derived from them. Consistency between the closed-world annotation and the 'authenticated user's companies' scoping is good; only pagination/size limits remain undisclosed.

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 resource and scope are front-loaded, and with no output schema the payload detail serves a purpose. However, it is delivered as one dense, run-on sentence enumerating a dozen return fields, which is hard to scan and pushes readability limits.

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, the description carries the burden of conveying what comes back, and it does so thoroughly (position aggregates, valuation history, metrics, people, funds, QSBS clocks, pro rata rights). For a single-required-param read tool this is close to sufficient; only error/empty behavior and result size are unaddressed.

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 the single 'slug' parameter, so the baseline of 3 applies. The description adds a small amount of provenance beyond the schema ('Slugs come from list_companies / search_companies') but no format or validation semantics.

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 opening clause states a specific resource and scope: one company, fetched by slug, restricted to 'the authenticated user's companies'. That scope plus the payload enumeration lets an agent distinguish it from list_companies/search_companies, which are named as the slug source rather than as equivalent retrieval 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?

It tells the agent where slugs come from (list_companies / search_companies), which is genuine routing help, and the 'authenticated user's companies' scope implicitly rules out arbitrary or third-party companies. But there is no explicit when-to-use-this-vs-X statement and no stated failure mode for an invalid or out-of-scope slug.

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