DecaData Odyssey Lite

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

Annotations already establish readOnly, non-destructive, closed-world behavior, so the description doesn't need to restate safety. It usefully adds behavioral detail the annotations lack: the ~380-company universe, that tier 3 is 'weekly only' (a data-granularity caveat), the (free) access note, and the exact payload fields.

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?

Two sentences, zero filler. The core action and search keys come first, followed by the return shape, with the tier caveat parenthetically attached where it is relevant.

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 output schema, the description takes on responsibility for return values and does so by listing ISIN, ticker, name, tier, and date bounds. The only meaningful gap is the limit/pagination behavior, which remains undocumented in both the description and the schema.

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 only 33% (only query is documented in the schema). The description partially compensates by explaining tier semantics ('1 largest, 3 smallest, weekly only'), which the enum alone cannot convey, but it says nothing about the limit parameter or its 1-400 range and default of 25.

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 and resource ('Search the ~380 US consumer companies') with the searchable keys (name or ticker) and even enumerates the returned fields. It is unambiguous on its own, but never names or contrasts with its siblings (get_sample, get_yoy_growth, quote_sales), so the agent gets no help disambiguating this from the other lookup tools.

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 implied rather than stated: searching by name/ticker and the note that an empty query returns the largest companies tell the agent roughly when this tool fits. There is no explicit when-to-use/when-not guidance and no mention of the alternative tools, so the agent must infer routing.

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

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

Annotations already establish readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that — that the call is free, fixed to Q1 2019, and available at daily or weekly granularity — but says nothing about rate limits, result size, or response format.

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 dense sentence with the scope and the value proposition front-loaded and no filler. Slightly clipped to the point of being a fragment, which costs a little clarity, but nothing is wasted.

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 one-parameter, no-output-schema tool this covers the data scope and cost, which is most of what an agent needs. However, it offers no way to know how daily versus weekly output is selected when no such parameter exists, leaving an actionable ambiguity unresolved.

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% and the single 'company' parameter is fully documented in the schema (ticker:, ISIN, isin: forms). The description adds nothing about the parameter, so the baseline 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?

The description names the resource and its scope concretely: Q1 2019 sales, units and panel stores for one company. It is clear this returns a preview dataset rather than an analysis, which separates it from get_yoy_growth and quote_sales, though it never uses an explicit verb like 'retrieve' and doesn't name those siblings directly.

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?

'Free, to see what the data looks like' implies the intended use case (data preview before committing to a paid/larger query), but there is no explicit when-to-use/when-not guidance or reference to the sibling tools that would serve the follow-up need. Usage is inferable but not stated.

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

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

Beyond the annotations (readOnly, non-destructive, non-idempotent), the description discloses substantial behavior: the pricing model and payment rail ($0.01, x402, USDC on Base), the exact time window (91 days ending at the latest reported quarter, never an unreported one), the comparison basis (same weekdays a year earlier), and the granularity/coverage dimensions. This is rich context the annotations cannot convey.

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?

It is a single front-loaded sentence that leads with the metric and price, and every clause carries information. It is dense and parenthetical-heavy, making it slightly hard to parse, but there is essentially no filler.

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 output schema, the description does carry the burden of explaining returns, and it partially does so by naming the vs_market_* fields and the company-vs-market comparison. Combined with annotations covering the safety profile, an agent has enough to call and interpret the tool, though return shape details remain partial.

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% and the single 'company' parameter already documents accepted formats (ticker, ISIN). The description adds nothing about the parameter itself, so the baseline of 3 applies when the schema fully carries parameter meaning.

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 names a specific metric (year-on-year growth in point-of-sale sales and units), its scope, and its unit of analysis (per panel store, company and market). This clearly differentiates it from siblings like quote_sales and find_companies, though it never names them. The core purpose is unmistakable.

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?

There is no explicit statement of when to choose this tool over siblings such as quote_sales or get_sample. The parenthetical 'vs_market_*, read it first' gives a within-response ordering hint, but that is about reading output, not about tool selection. Usage is implied rather than guided.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds real value by disclosing that the quote is free and that it returns an x402 purchase URL, but says nothing about rate limits, authentication for the buy step, or price currency/units.

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 compact sentence with no filler, and the core output (exact price) is front-loaded. The phrasing 'price of a window of daily or weekly sales and units' is slightly convoluted but still parses cleanly.

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 output schema, the description correctly compensates by naming the return values (price plus HTTP buy URL), which is the key missing piece. It still leaves gaps around price units/currency, behavior when the requested window is unavailable, and the relationship to the sibling lookup tools.

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 75%, so company, from, and to are largely documented in the schema itself. The description confirms the daily/weekly dimension (mapping to freq) and the notion of a date 'window', but adds no format, default, or syntax detail beyond what the schema already provides.

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 concrete verb+resource: pricing a window of daily or weekly sales/units, and returning both the price and a purchase URL. This is clearly distinguishable from find_companies, get_sample, and get_yoy_growth, though it never explicitly names what those siblings do differently.

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 parenthetical '(free)' and the mention of a buy URL imply this is the pre-purchase quoting step, which is useful implied guidance. However, there is no explicit statement of when to use this versus get_sample or get_yoy_growth, and no stated prerequisites (e.g., company must be resolvable via find_companies).

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