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

Annotations already cover read-only and open-world access, but the description adds material context annotations cannot convey: a metered price of $0.002 USDC per successful call via x402 with failed calls not charged, plus the provenance caveat that figures are user-reported and therefore not authoritative. What it omits is failure behavior when a company or job family slug has no data, and any caching or rate-limit expectations.

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-loaded with the scope in the opening clause, then the returned measures, then constraints and pricing. Dense but almost every element carries information; the enumeration of percentile fields is somewhat redundant against the output schema and is the one place a word could be saved.

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?

For a two-parameter read with an output schema, the definition covers what an agent needs to decide and pay correctly: scope, geography, currency, data reliability, and cost model. The remaining gap is edge behavior (unknown slug, sparse sample size) which the output schema cannot express and the description leaves unstated.

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 100% — both company and jobFamily already document slug format with examples and the software-engineer default. The description reinforces the compound scope ('one company and job family') and adds the US/USD constraint that affects interpretation of results, but contributes no new syntax or format guidance. Baseline 3 applies.

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 specific verb+resource (retrieve tech compensation for one company and job family from Levels.fyi's public salary page) and enumerates the returned measures: total-comp, base, stock, bonus percentiles p10-p90, sample size, and per-level average package. This is clearly distinguishable from the surrounding job-listing siblings and the adjacent comp sources (jobs_glassdoor, jobs_payscale) because it is explicitly a salary-page lookup keyed by company + job family.

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: the example 'google + software-engineer' and the phrase 'one company and job family' signal the calling pattern, and 'United States figures' scopes the applicability. There is no explicit when-to-use/when-not statement and no pointer to jobs_payscale or jobs_glassdoor as alternatives for non-tech or non-US compensation, so the agent must infer routing.

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