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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description adds valuable behavior: signals are facts not ratings, empty signal list means nothing found rather than soundness, incomplete 404 sections are filled, and the caller must check sections_included before concluding absence. This goes beyond the structured hints 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 dense but well organized: it opens with the core value proposition, then gives the comparison to siblings, then the interpretation caveat, then the sections_included caution. Every sentence adds information and none are redundant with the schema or annotations.

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?

Given the output schema exists and annotations carry the safety profile, the description covers what an agent needs to invoke correctly: when to use it, what it returns at a high level, how to interpret empty signals, and how to control size/cost via parameters. Nothing critical is missing for a read-only aggregation tool.

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 five parameters well. The description adds context beyond the schema, particularly the round-trip cost implication of include_officers and the caution about verbose payload size. It does not re-describe every parameter, which is appropriate given full schema coverage.

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 uses a strong verb phrase ('Everything worth knowing about one company in a single call') and enumerates the exact resources covered: profile, serving officers, outstanding charges, insolvency cases, and signal list. It also explicitly contrasts with sibling calls (get_company, get_officers, get_charges, get_insolvency), making differentiation 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?

It explicitly states when to use this tool instead of the four separate sibling tools, noting the round-trip advantage and the fact that it fills in sections that Companies House reports as 404. It also warns against misinterpreting empty signal lists and directs users to check sections_included, and implicitly routes name-only lookups to find_company via the schema description.

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 mark the tool as readOnly, openWorld, idempotent, and non-destructive, so the bar for additional disclosure is met. The description goes beyond annotations by explaining the shortlist contents, the disambiguation flag, and the real risk of confidently answering about the wrong company when names collide. This is valuable behavioral context not present in the schema or annotations.

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 three sentences, each earning its place: the first states the core function, the second gives routing guidance, and the third warns about a critical failure mode. It is front-loaded with the action and resource, and there is no filler or restatement of the tool name.

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 search tool with a 100%-covered schema, an output schema, and strong annotations, the description is complete. It covers purpose, when to use it, what results look like, and how to handle ambiguity. Nothing needed for correct invocation 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%, so the schema fully documents all four parameters. The description adds no new parameter semantics beyond what the schema already provides, though it does reinforce that the query can be a name, trading name, or number, which matches the schema. Baseline 3 is appropriate because the schema carries the full burden.

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 action ('Search Companies House for a UK company'), specific inputs (name, trading name or number), and a specific output (shortlist with status, type, incorporation date). It distinguishes this tool from siblings by explicitly positioning it as the starting point when you have a name rather than a number, which differentiates it from get_company and similar number-based 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?

The description gives direct usage guidance: use this tool whenever you have a name rather than a number, because every other tool in the server needs the number. It also gives a concrete behavioral rule: when disambiguation_needed is true, ask the user which company they meant rather than blindly taking the first result.

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/idempotent annotations, the description discloses a key behavioral quirk: officer records are per-appointment-identity rather than per-person, so common names return many candidates and appointment count plus date of birth separate them. This is exactly the kind of caveat an agent needs before invoking or interpreting results.

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 opening sentence, followed by return values, usage guidance, and a caveat. Every sentence adds useful information and there is no padding or redundancy.

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?

Covers what the tool does, when to use it, what it returns, a key data-model caveat, and the downstream tool to call next. With a complete input schema and an output schema present, nothing essential is missing for correct selection and invocation.

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?

The input schema already describes all four parameters with 100% coverage, so the baseline is 3. The description adds no param-specific detail beyond 'by name', which the schema already conveys; it relies on the schema for 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?

States the exact operation — 'Search Companies House for a company officer by name' — and scopes it to directors, secretaries, and LLP members. It also clarifies the output is candidate officer IDs with appointment counts, which distinguishes it from company search and officer-appointment retrieval 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?

Gives an explicit usage condition: use it when you have a person and want the companies they are involved in, and names get_officer_appointments as the next step. It does not spell out when-not-to-use it versus siblings like get_officers, but the context is otherwise clear.

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?

While annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, the description adds meaningful behavioral context: outstanding_count is derived because Companies House does not report unsettled charges, and floating charges deserve closer scrutiny. This goes beyond the structured 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 four sentences and each contributes value: what the tool returns, an important derived-field nuance, a risk heuristic, and an input requirement. It is appropriately front-loaded with the core definition, though slightly longer than strictly necessary.

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?

Given the output schema exists and the tool is a read-only retrieval operation, the description covers the essential context: what charges are, why the derived field matters, a caution about floating charges, and the required identifier. Minor gaps like pagination are not critical given the output 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 100%, so the schema already fully documents company_number and verbose. The description adds no new parameter-specific detail beyond restating that a company number is needed, which the schema already covers. A baseline 3 is appropriate.

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 clearly identifies the resource (secured debt/charges registered against a company) and the specific attributes returned: holder, coverage, creation date, and satisfaction status. This distinguishes it from sibling tools like get_company or get_psc, which address different company data domains.

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 gives a concrete use case ('when screening a supplier or a debtor') and states the required input ('Needs a company number'). It does not explicitly call out alternatives or when not to use the tool, but the schema does point to find_company when only a company name is available.

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 that the tool is read-only, idempotent, and non-destructive. The description adds valuable behavioral context beyond annotations: it returns derived flags that Companies House itself does not provide, such as overdue indicators, charges/insolvency history presence, and recent incorporation. It also repeats the input constraint that only a company number is accepted. No contradiction with annotations.

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 longer than minimal but every sentence earns its place: first the returned data inventory, then the derived flags, then the intended use case and prerequisite. It is front-loaded with the resource and scope, and there is no filler or tautology.

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?

Given the read-only annotations, complete parameter schema, and existing output schema, the description covers everything an agent needs to select and invoke this tool correctly: what it returns, what derived flags it adds, when to use it, and how to handle a name-only input. No critical behavioral or prerequisite information 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%, so the schema already fully documents both company_number and verbose. The tool description reinforces the 'do not pass a name' caveat and the find_company prerequisite, but it does not add meaningful parameter-level semantics beyond what the input schema already provides. Baseline 3 is appropriate.

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: it returns the registered profile for one UK company, and enumerates the exact fields included (legal name, status, type, incorporation date, registered office, SIC codes, due dates). It also distinguishes the tool from find_company by clarifying that get_company needs a company number and does not accept a name.

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 says to use this tool to verify a company is real and active before relying on it, and directs agents to call find_company first if only a name is available. It does not explicitly mention when to prefer related sibling tools like get_charges or get_insolvency, but it does clarify that it returns only derived flags about those topics rather than full details.

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 description adds genuine behavioral context beyond the read-only annotations by explaining that filing descriptions come back as un-translated Companies House template keys and why partial translation was avoided. It also hints at response volume by recommending category filtering, which is useful for an agent deciding how to call 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 description is compact and front-loaded: it states the core purpose first, then use cases, then an important output-format caveat, then a filtering tip. Every sentence earns its place without verbose framing or redundant schema repetition.

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?

Given the output schema and fully described input parameters, the description covers the important operational details: what filings are included, how keys are represented, why translation is skipped, and how to reduce volume. It could be slightly stronger by mentioning pagination behavior explicitly, but the start_index parameter and output schema already carry that burden.

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 parameters are fully documented in the schema. The description adds only minimal parameter-related guidance, such as using category to cut volume and requiring a company number, which mostly restates what the schema already says.

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 statement of what the tool returns — "What a company has filed and when" — and lists concrete filing types such as accounts, confirmation statements, and officer changes. This clearly distinguishes it from sibling tools like get_company or get_officers by focusing on filing history events.

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 explicit use cases: judging whether a company files on time, seeing when accounts were last made up, and watching a competitor's filing cadence. It also notes the need for a company number and suggests filtering with category, though it does not explicitly name alternative tools or state when not to use it.

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 readOnly/idempotent annotations, it discloses a genuinely surprising API quirk: no history yields a not-found error rather than an empty list. This prevents an agent from misinterpreting an error as a failure of the tool itself.

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 tight sentences: what the tool returns, when to use it, and the one edge case an agent must know. Every sentence earns its place and important constraints are front-loaded.

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 re-specify return fields. It covers purpose, trigger, error behavior, and required input, and annotations cover safety, making this complete for reliable invocation.

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 company_number and verbose are already documented in the schema. The description adds only a high-level 'Needs a company number' restatement, 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 a specific resource (insolvency cases registered against a company) and the meaningful output (proceeding type, key dates, practitioners). It also ties it to get_company's has_insolvency_history flag, which differentiates it from sibling tools without needing to inspect schemas.

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 explicit trigger conditions: call it when get_company reports has_insolvency_history or as part of a credit/supplier risk check. It does not enumerate exclusions or alternatives, but there is no dedicated sibling insolvency tool, and 'Needs a company number' clarifies a prerequisite.

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, and the description adds behavior beyond that: the result includes both current and historical appointments ('is or has been appointed to') and is suited for spotting dissolved-company history. No annotation contradiction exists.

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 tightly written sentences: core function, illustrative use cases, and the key input requirement. Every sentence contributes new information and the most important facts are front-loaded.

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 list endpoint with a full output schema and fully documented parameters, the description covers the essential context: what data is returned, why an agent would use it, and where the required identifier comes from. Nothing critical 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%, so the schema carries most parameter documentation. The description adds important semantic value for officer_id by stating it must come from get_officers or find_officer and not from a name, which prevents a common misuse.

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 the exact resource ('Every company an officer is or has been appointed to') and positions the tool as the conflict-of-interest/director-network lookup. This clearly distinguishes it from siblings like get_company or get_officers, which have different scopes.

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 concrete when-to-use scenarios: running across a board to expose undeclared shared directorships, or checking a person's history of dissolved companies. It does not explicitly list sibling alternatives or exclusion conditions, but the use-case framing is clear enough to route an agent correctly.

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 mark the tool read-only and idempotent, and the description adds non-obvious behavior: service addresses are withheld for privacy unless verbose is set. It also discloses that verbose returns a much larger raw payload, which helps the agent set expectations beyond what the annotations 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?

Four sentences, each earning its place: the tool's output, the use cases, the privacy caveat, and the prerequisite. The most actionable information is front-loaded, and there is no redundant wording.

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 does not need to explain return values. Combined with full schema documentation for all parameters, the description covers purpose, usage context, privacy behavior, and how to chain with sibling tools, so nothing critical 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%, which sets a baseline of 3. The description adds extra meaning for company_number by emphasizing it cannot be a name and requires find_company first, and for verbose by explaining the privacy trade-off. The remaining parameters are adequately documented in 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: get officers of one company, including current and resigned. It also distinguishes itself from related siblings by noting each result carries an officer_id to pass to get_officer_appointments, making it clearly different from find_officer or get_officer_appointments.

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 gives when to use the tool: to see who runs a company or as the first step in a conflict-of-interest check. It also names the prerequisite (company number) and directs the agent to call find_company first if only a name is available.

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, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavior beyond the annotations: it explains the returned fields, states that interests can be current or ceased, and discloses the edge case where a statement is returned in the name field instead of a person. This provides actionable behavioral context without contradicting the annotations.

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 dense but every sentence earns its place: it states the core purpose, gives usage context, distinguishes from siblings, explains the return data, and covers a key edge case. The most important routing signal is front-loaded with 'Who OWNS a company,' and the final 'Needs a company number' is a useful practical requirement. There is no filler or repetition.

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 an output schema and 100% schema parameter coverage, the description is complete. It explains what the tool returns, when to use it, how it differs from related tools, how to handle the statement fallback, and the prerequisite of a company number. Pagination is already covered by the schema's start_index and items_per_page descriptions, so no further behavioral detail 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%, so the input schema already documents all four parameters thoroughly, including company_number format, verbose behavior, pagination offset, and items_per_page. The description adds only 'Needs a company number' and the hint to call find_company if only a name is available, which the schema already states. This is the baseline 3 case: the schema carries the parameter-semantics burden and the description does not need to compensate.

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 the concrete, memorable phrase 'Who OWNS a company' and immediately identifies the resource: persons with significant control, including shareholding bands and control mechanisms. It also differentiates itself from related tools by explicitly stating that get_company will not answer ownership questions and that ownership is a different question from get_officers, so an agent can distinguish it from siblings without opening schemas.

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 gives explicit when-to-use guidance: 'Use this for any question about ownership, shareholders, beneficial owners or who is ultimately behind a business.' It also names exclusions and alternatives, warning that get_company will not answer this and directing users to find_company if they only have a company name. This is exactly the kind of routing context an agent needs.

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 mark this read-only/idempotent, but the description adds substantial behavioral context: one row per company, signal codes only, unresolved names returned with candidates rather than guessed, not_screened entries with reasons for rate-limit skips, and officer handling with cost implications. None of this is visible in the annotations.

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 but every sentence contributes: usage guidance is front-loaded, the alternative is named early, and edge-case behaviors are explained in logical order. No filler or repetition of schema content.

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?

Given the tool's complexity and the presence of an output schema, the description covers all necessary operational details: limits, return shape, unresolved/not_screened behavior, signal-code usage, and officer cost trade-offs. Nothing an agent needs to safely invoke it 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, but the description adds meaningful context beyond the schema: it explains that names matching multiple companies are not guessed, unresolved results include candidates, and include_officers carries an extra request cost. This helps an agent choose parameters more wisely.

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?

Description states a specific verb and resource ('Screen a list of companies') and immediately clarifies it is for MORE THAN ONE company. It explicitly contrasts with company_snapshot, so an agent can distinguish the intended use without inspecting schemas.

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?

Provides explicit when-to-use conditions: lists, comparisons, batches, and anything with several names or numbers. It also names the alternatives (company_snapshot for detail, repeated calls as the less efficient option) and explains when to switch.

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