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

Annotations already cover readOnly/idempotent/non-destructive/openWorld, so the safety profile is free. The description adds genuine context beyond that: it discloses the underlying mechanism ('deep research pipeline with the earnings_preview template') and a concrete latency window (30-90 seconds), which materially affects how an agent should set 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 verb and resource, then the component list, then mechanism, latency, and usage. The enumerated analysis list is long but earns its place by defining the report's scope. Slightly verbose, but every sentence carries information.

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 composite report tool this is complete: an output schema covers return values, annotations cover safety, schema documents both params, and the description adds scope, mechanism, latency, and when-to-use. An agent has everything needed to select and 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 description coverage is 100%, so both ticker and question are already documented in the schema, including the ticker example. The description adds no format or syntax detail about the optional question parameter beyond what the schema provides, so the baseline of 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 (Generate) and resource (pre-reporting season earnings preview report for an NZX company), then enumerates exactly what the report contains (consensus vs price, guidance accuracy, tone trends, surprise probability, etc.). This distinguishes it clearly from atomic siblings like get_earnings, get_earnings_surprise, and get_analyst_consensus, which return individual metrics rather than a composite preview.

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?

Gives explicit when-to-use context: 'Use when a user asks about upcoming results, earnings expectations, or wants to prepare for a reporting season.' Solid routing signal, but it never names an alternative (e.g., use get_earnings_surprise for just the probability) or states when not to use it, so it stops short of full exclusion guidance.

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