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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral detail: values retain the company's stated scale, GAAP-to-non-GAAP reconciliation includes its stated bridge, and transcripts are not sources. These details explain what the tool does and does not return beyond the schema, enriching the agent's mental model without contradicting annotations.

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 dense but efficient, with every sentence earning its place. It front-loads the core purpose, then details the parameter-dependent output, and ends with two important constraints (transcripts not sources, reconciliation bridge). There is zero fluff, and the structure leads with the most critical information for an agent deciding whether to use the tool.

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?

The tool has no output schema, so the description must explain the return format. It does: 'period, filing date, source quote and exactly comparable year-over-year change.' It also specifies the scale handling and reconciliation behavior. While it doesn't mention pagination or limits, the tool is a read-only lookup with only two parameters and the description covers the essential facets an agent needs to invoke 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% and the schema already describes the parameters, but the description goes further. It explains the metric parameter's behavior in detail: matching case-insensitively, listing candidates when multiple metrics match, and omitting for the latest reading. It also clarifies that values retain the company's stated scale, which is a semantic nuance not fully captured by the schema. This adds significant meaning beyond the structured fields.

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 verb ('Get'), a precise resource ('company-stated operational and non-GAAP KPIs extracted from written 8-K earnings releases and 10-K/10-Q MD&A'), and details the output fields (period, filing date, source quote, YoY change). It also distinguishes itself from related tools by explicitly limiting sources to written filings, not transcripts or other data types, so an agent can separate it from siblings like GetEarningsCallTranscript or GetNonGaapBridge.

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 gives clear context about when to use the tool (to get company-stated KPIs from written filings) and an explicit exclusion: 'Earnings-call transcripts are not figure sources.' It provides a 'when-not' but does not name specific alternative tools for transcript-based data, so it stops short of a full 5. The parameter usage guidance (omit metric for latest reading, pass metric for history) also informs when to call with or without the metric.

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