Company Profile

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: default response size (~3KB), the fact that optional sections are fetched via parallel API calls, and the critical warning that a null metric means 'not published' and must never be treated as 0. It also discloses that the stock itself is included in the peers table and flagged is_self. This goes beyond the annotations without contradicting them.

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 well-structured with a clear lead sentence, bullet-like sections, and an example. It is longer than average, but every section earns its place: the peers detail is dense but necessary to prevent misinterpretation of null values and is_self. The post-tool suggestions are arguably beyond the core tool description and could be trimmed, but they are clearly separated and actionable. Slight over-length keeps it from a 5.

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 read-only, idempotent tool with no output schema, the description is remarkably complete. It tells the agent what the base response contains, what optional sections exist, how to request them, what the peers table includes, how to interpret nulls, and what to suggest to the user afterward. The only thing missing is a note about error cases or rate limits, but those are not expected in a tool description and the annotations cover safety.

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 the schema already documents all four parameters. The description adds meaning beyond the schema by explaining what the 'include' values actually return (e.g., technicals = RSI, SMA, EMA, MACD, Bollinger Bands, ATR, ADX; ratings = analyst consensus with counts and percentages; peers = comparable-company table with specific columns). It also clarifies that 'symbol' is required even though the schema marks it as not required, and that 'ticker' and 'identifier' are aliases. This is meaningful added value.

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 detailed company overview' and enumerates the exact content (sector, about, pros/cons, fundamentals, growth metrics, current quote). It clearly distinguishes itself from siblings like get_live_quote, get_financials, and get_stock_news by stating what is included in the base profile and what is not.

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 explicitly tells the agent when to use the 'include' parameter to add optional sections, and even gives an example ('include ["technicals", "ratings"]'). It also names sibling tools for deeper dives (get_financials, get_forecasts, get_stock_events, shareholding patterns), providing clear routing guidance. The only minor gap is not stating when NOT to use this tool, but the alternatives are named.

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