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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful behavioral content in the form of returned signal categories and the 'frozen-price or old-scorecard flags', which hint at data-staleness conditions, but it discloses nothing about rate limits, pagination, or cost of a 6-token comparison.

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?

Front-loads the token count and the action, which is good, but the middle is a dense, comma-chained metric dump that some readers will parse poorly. Given 0% schema coverage the enumeration earns its place, yet the nesting ('revenue_figures per token (30-day annualized pace and real last-12-months revenue, P/S on both)') is hard to follow.

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 correctly takes on the burden of describing what comes back and lists most of the metric surface, so it is broadly usable. It still omits how the `fields` parameter narrows results and the 18-item cap, and lacks any note on ordering or comparability caveats across tokens.

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 0%, so the description must carry semantic load, and it does partially — it expands metric labels like 'health with six pillar scores' and 'revenue_figures ... 30-day annualized pace'. However, it never explains the `fields` selection parameter or its 18-item cap, and its 'Two to six tokens' phrasing mildly conflicts with the schema's minItems of 1.

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?

States a concrete action and resource: 'Two to six tokens side by side' with an enumerated set of comparison metrics. It reads clearly as a multi-token comparison tool, implicitly distinct from single-token siblings like tc_get_token, though it never names an alternative to differentiate itself explicitly.

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?

Usage is only implied by the 'two to six tokens' constraint and the list of comparable metrics; there is no explicit when-to-use statement or when-not/exclusion. The agent can infer that this is for multi-token comparison rather than single lookups, but nothing routes it between this and tc_get_token, tc_screen, or tc_brief.

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