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

Annotations cover safety (readOnly/idempotent/non-destructive), and the description still adds real behavioral detail: the n>=10 threshold, name-matching behavior shared with get_valuation_multiples, the INSUFFICIENT DATA fallback instead of estimation, and per-row flagging of unmatched names and industry-group ids. That is exactly the disclosure that prevents an agent from misinterpreting sparse output.

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?

Dense and front-loaded — the core comparison behavior comes first, then the fallback rules, then the sibling routing. Slight deduction because the leading 'Read-only.' restates annotation fields and the first sentence is heavily packed.

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 an output schema present, the description needn't explain return structure, and it still covers thresholds, fallbacks, name resolution, and the alternative tool. Nothing an agent needs to select or invoke this correctly is missing.

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%, so the baseline is 3; the schema already documents metric values, the 2-6 item constraint, and every size_bracket enum with dollar ranges. The description adds only marginal framing (one metric at a time, size_bracket for a single bracket) rather than new semantics.

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?

Names a specific verb+resource (compares 2-6 industries side by side on one metric) and enumerates exactly what output each row carries: median multiple, 25th-75th percentile, and deal count n per EV bracket. A reader can distinguish it from get_valuation_multiples without opening either schema.

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 an explicit routing rule with the sibling named: 'Use it for which sells for more, X or Y? questions; use get_valuation_multiples for one industry's full breakdown.' It also states the condition for size_bracket (single-bracket comparison vs. omit for all brackets).

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 read-only annotations, the description discloses important behavior: only years with at least 10 disclosed deals per metric appear, missing years are listed as gaps and never interpolated, and many sub-verticals have few or no years. This is exactly the kind of caveat an agent needs before invoking the tool.

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 key scope is front-loaded, and the description is dense with useful information rather than filler. Every sentence contributes either scope, data behavior, caveats, or routing guidance.

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 is complex enough to need caveats, and the description covers the year range, threshold behavior, gaps, non-interpolation, and sibling routing. With annotations, full schema coverage, and an output schema already present, nothing important is missing.

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 schema already documents metric and industry thoroughly, including enum values and plain-English mapping. The description reinforces that only one sub-vertical is used and that metric may show one or both multiples, but it adds little beyond the structured schema.

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 and resource: year-by-year history for one sub-vertical, with named metrics, date range, percentiles, and deal counts. It clearly distinguishes itself from get_valuation_multiples by contrasting per-year trend data with pooled figures by deal size.

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?

It gives an explicit use case ('are multiples rising or falling for X?') and names the alternative tool for pooled figures by deal size. The condition that selects this tool versus get_valuation_multiples is therefore clear and actionable.

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 readOnly/idempotent/non-destructive, but the description adds substantive behavior: cells with fewer than 10 deals are withheld and never estimated, the data window is 2018-2026, and group ids return per-sub-vertical medians rather than a single figure. What is missing is a note on latency/caching or the response shape, but the critical statistical caveat is disclosed in detail.

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 the core question and the read-only constraint, and every clause carries information. It is dense, but the four sentences pack return shape, coverage period, suppression rule, and alternatives without 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?

An output schema exists, so return-field documentation is not required, and the description still sketches the result shape (IQR, n, brackets). Combined with the explicit exclusion of company-specific valuation and the sibling routing, an agent has everything needed 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%, so both parameters are fully documented in structured fields. The description adds that an industry group id yields a median per sub-vertical, which is return behavior rather than parameter meaning, and it never mentions size_bracket at all. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

Specific verb and resource: answers the multiple question for ONE industry and returns median EV/EBITDA and EV/Revenue with IQR and deal counts. It explicitly bounds scope ('Population medians only: it does not value a specific business'), which separates it from a business-valuation tool.

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?

Names both alternatives and the condition that selects them: compare_industries for side-by-side multi-industry views and get_multiples_trend for year-by-year history. It also implies list_industries as the source of valid ids via the schema, leaving no routing ambiguity.

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?

The 'Read-only' opener merely restates readOnlyHint=true, earning no credit, but the description adds genuinely new behavioral context: it takes no input, returns both ids and display names, and flags that starred ids have published multiples in the open dataset. It does not discuss ordering or dataset size, keeping it short of a 5.

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?

Three short sentences, all front-loaded: read-only status, then what is returned, then the routing advice. No filler and nothing buried at the end.

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?

An output schema exists so return values need not be explained, yet the description still tells the agent what the payload means (ids, display names, starred ids with multiples) and how to use the result downstream. For a no-argument discovery tool this is fully sufficient.

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?

There are zero parameters, which is the baseline 4 case, and the description correctly confirms 'Takes no input' so the agent will not hunt for optional filters. No further parameter semantics are needed.

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: 'Lists every industry and sub-vertical ExitValue.ai tracks, with ids and display names.' It also scopes the content (which taxonomy, what fields, and the * marker for published multiples), so an agent can distinguish it from get_valuation_multiples and compare_industries without reading either schema.

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?

Explicitly says 'Use it first when you are unsure of an id' and notes that 'the other tools accept these ids or plain-English names' — it names the alternative path and the condition that selects this tool. That is both when-to-use and when-you-might-skip guidance.

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