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

Beyond the readOnlyHint=true annotation, the description discloses significant behavioral nuances: the narrative shift 'is derived from approved bullets and is not separately verifier-approved', comparisons 'use filed GAAP XBRL facts, never estimates', ordering is 'Newest quarter first', and quarters can be absent from the sequence because only approved briefs appear. These caveats prevent the agent from misinterpreting missing quarters or over-trusting the shift metric.

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 long (four sentences) but every sentence earns its place: each adds a disambiguating constraint ('not analyst consensus', 'not separately verifier-approved', 'quarters can be missing'). It is front-loaded with the core content definition before the caveats. The density is justified given the tool's complexity, though it could trim some redundancy around ordering.

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 retrieval tool with no output schema, the description lists the return elements (TL;DR, points, quotes, shift, guidance deltas, reported quarter vs guidance) plus all caveats (verification status, missing quarters, XBRL facts). Annotations already cover the read-only safety profile. The only gap is that the exact return structure/field naming isn't specified, but the content inventory is sufficient for an agent to call it correctly.

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% — every parameter (ticker, limit, fiscalYear, fiscalQuarter) is already well-documented, including the clamp range for limit and the exact-period semantics for the fiscal fields. The description's 'Newest quarter first' and 'Omit both period fields for newest briefs' reinforce schema text but add little new meaning. Baseline 3 is appropriate since the structured schema carries the parameter burden.

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 opens with a specific verb and resource — 'Get the AI Earnings Brief for a company's recent earnings calls' — and enumerates the exact content: verifier-approved TL;DR, bullish/bearish points, verbatim pull-quotes, and a narrative shift. It also carves out the data provenance ('company guidance, not analyst consensus... filed GAAP XBRL facts, never estimates'), which sharply distinguishes it from siblings like GetGuidance, GetEarningsCallTranscript, and GetEarningsCallToneAndThemes without naming them.

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 description provides rich context about what the tool returns and its data constraints ('Only calls with an approved brief appear, so quarters can be missing from the sequence', 'Newest quarter first'). However, it never explicitly names sibling alternatives or states when NOT to use this tool in favor of GetGuidance, GetEarningsCallTranscript, or GetFinancialStatement. Usage context is implied through content specificity, but no explicit routing or exclusions are given.

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