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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile needs no restating. The description contributes one genuinely useful behavioral fact: this returns the account the connector is bound to, i.e. it takes no account identifier and is implicitly scoped. It says nothing about freshness, caching, or whether quota counters are real-time, which for a usage-metering endpoint would be valuable.

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?

A single front-loaded sentence identifying the resource first, then the payload. Every clause names a distinct returned field, so nothing is filler. The middle clause ('this month's contact reveals and export rows used and left') is slightly tangled and could be split for readability.

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 parameters, no output schema, and full annotation coverage, the description carries the entire burden of explaining return contents — and it does so by listing the data categories. What remains unstated (whether 'used and left' counters reset monthly, whether assistants include metadata) is minor for a simple account getter.

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?

The tool takes zero parameters, so the baseline is 4; the schema is empty and the description correctly does not invent parameters. The field enumeration tells the agent what to expect back, which is the only meaningful 'parameter-like' information left.

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 ('The Corridome account the connector works for') and enumerates the fields returned: plan, contact reveals and export rows used/left, alerts email setting, connected assistants. It is clearly distinguishable from the sibling get_/list_ tools, which all target other resources (company, deal, firm, fund, folder). It stops short of explicitly naming a sibling it replaces, so a 4 rather than 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?

Usage is only implied by the content list: an agent infers 'call this when you need account-level plan, quota, or alert-email information.' There is no explicit when-to-use trigger, no mention of pairing it with set_alerts_email, and no when-not guidance. Adequate but entirely inferential.

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