Sell My Company Data

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: it sends nothing about the user (privacy) and that it takes no input, which reassures an agent worried about side effects. No rate limits or failure modes are mentioned, but none are plausible for a static checklist.

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 with the imperative "Call this first" front-loaded, followed by what it returns and the privacy guarantee. Every sentence carries distinct information and nothing is padded.

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 the description needn't detail return values, yet it still summarizes the three payload components (per-system counts, privacy rule, missing-number handling). For a zero-parameter read-only lookup this is fully sufficient to call 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?

Zero-parameter tool, so the baseline is 4. The description confirms "takes no input," which is redundant with the empty schema but harmless and consistent with additionalProperties=false.

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 ("returns what to count in each kind of system") and enumerates the system categories covered (chat, CRM, support, docs, code, email, project, finance), plus the privacy rule and missing-number handling. Combined with the title and "call this first," an agent can tell this is a prerequisite checklist distinct from estimate_data_value and request_offer without opening any 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?

"Call this first" gives an explicit ordering constraint that routes the agent ahead of the estimating siblings. However, it never names those siblings as alternatives, nor does it state when this tool can be skipped (e.g., if the agent already knows what to count), so there are no exclusions.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real context beyond them: 'stores nothing and contacts nobody,' the below_bar flag behavior for small/young companies, the 'always present it as an estimate' caveat, and the instruction to ask rather than guess. These are behaviors an agent could not infer from the schema.

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?

Purpose is front-loaded in the first sentence, followed by privacy constraints and edge-case behavior in a logical order. Six sentences is on the longer side but nearly all carry non-redundant information; slight tightening would be possible.

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 need not explain return values, and it still usefully explains the below_bar band and the indicative-range nature of the result. Privacy rules, missing-data handling, and framing guidance are all covered, leaving nothing an agent needs unaddressed.

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 description goes further by telling the agent what content may enter the parameters ('staff count, founding year, country and the list of systems with counts and date ranges') and, critically, what must never enter them (message text, customer names, file names, personal data) — a constraint the schema cannot express.

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 object ('Estimates what the company's operational data might fetch when licensed to AI labs'), plus what it returns ('an indicative range'). This is clearly distinct from the siblings assessment_checklist and request_offer, which the description's framing makes obvious without naming them.

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 clear operating context: send only summary numbers, ask the user for missing values rather than guessing, and expect a marked-down band for companies under 20 staff or 3 years. It does not explicitly route between this tool and request_offer, so it stops short of full alternative guidance.

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?

Adds real context beyond the annotations: it warns the send is irreversible, clarifies that calling twice creates two requests (explaining the non-idempotent behavior in practice), and reassures that company data is not shared or made accessible. This goes past the raw destructive/openWorld flags into what the agent actually needs to know before committing.

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?

Five sentences, front-loaded with purpose, then preconditions, then risk/idempotency notes. Every sentence carries weight — the read-back requirement, consent gate, irreversibility, data-scope disclaimer, and duplicate-call warning are all distinct and actionable.

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 no explanation, and the description covers authorization, irreversibility, and duplication risk well. The minor gap is sequencing with siblings — it doesn't say whether estimate_data_value or assessment_checklist should precede this call, leaving the agent to infer the workflow order.

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 73%, so the schema already documents most fields (consent, country enum, systems sub-object, is_authorized). The description only gestures at payload content via 'contact details and the summary numbers' without mapping to the 15 parameters or clarifying what 'summary numbers' covers. Adequate but no added meaning beyond the 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?

States a specific verb and resource ('Sends the owner's contact details and the summary numbers to Sell My Company Data so the team can prepare a real offer') and explicitly scopes what it does NOT do ('does not share or give access to any company data'), which separates it from estimate_data_value and assessment_checklist style siblings.

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 hard preconditions in caps: only after the user explicitly asked for an offer AND contact details were read back and confirmed. It also conditions the consent flag ('Set consent to true only if they agreed to be contacted'), so the agent has explicit gating rules rather than inferred ones.

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