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

Annotations only carry readOnlyHint=true and a title, so the description carries the transparency burden. It adds meaningful operational traits beyond the annotation: the tool performs cross-catalog synthesis ('Priced B2 (cross-catalog synthesis)'), has a concrete per-call cost ($0.05), and a pointer to authoritative pricing ('See apis://prices'). For an agent making cost-aware decisions, this is valuable behavioral context that the readOnlyHint alone does not provide. The 'UNDERSTANDING' framing is consistent with read-only semantics, so no contradiction.

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 compact at three sentences, with the core purpose front-loaded before pricing details. Each clause earns its place, and the pricing pointer is the only auxiliary sentence. It loses a point for the cryptic 'UNDERSTANDING'/'Priced B2' jargon, which requires proprietary knowledge to fully parse, but overall it is efficiently organized and free of 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?

With no output schema, the description carries the burden of explaining returns, and it does convey the return concept ('weakest investment dimensions'). However, the output shape remains structurally vague (list of dimensions? scored?), the required input semantic for 'slug' is never made explicit, and no behavioral guarantees (e.g., nothing about how the synthesis is computed) are given. It is adequate for a simple read-only tool but leaves the agent to infer what the result actually looks like.

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 50%: the required 'slug' parameter has no description in the schema, while 'context' is well-documented. The description partially compensates by implying slug identifies the company ('A company's weakest investment dimensions'), but it never explicitly states that slug is the company identifier or describes its expected format. The 'context' parameter is fully covered by the schema, so description credit is only needed for slug, which it only half-provides.

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 a specific output concept: 'A company's weakest investment dimensions — where it is thin and a vendor could sell in.' This identifies both the resource (a company) and the synthesized result (weakness dimensions with vendor sell-in opportunities), which is more specific than a generic name like 'company_gaps'. It earns a 4 rather than 5 because the verb is implicit (the 'UNDERSTANDING' prefix is a category label, not an action verb) and it doesn't distinguish itself from siblings like gap_analysis, industry_gap_analysis, or get_company_insight.

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 only usage-adjacent content is the pricing model ('$0.05 per call under pay-as-you-go; included in Understanding and Influence'), which hints at cost considerations but says nothing about when to choose this tool versus alternatives. With highly similar siblings present — gap_analysis, industry_gap_analysis, insights_dimensions, get_company_insight — the absence of any when/when-not routing is a real gap.

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