EnrichGrid

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

With no annotations, the description carries the full behavioral burden. It usefully discloses the cost model ("1 credit if found") and enumerates returned firmographic fields, but it omits authentication needs, not-found behavior, and whether the response is a flat object or structured payload.

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 a single efficient sentence with the core action and identifier formats front-loaded, followed by the returned fields and credit cost. Every phrase contributes useful information.

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 enrichment tool with no output schema, the description lists the firmographic fields returned and the cost condition. However, it does not fully specify the return structure or error/not-found behavior, which would matter without an output schema and annotations.

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 identifier parameter is already documented in the schema. The description reinforces the acceptable identifier types but adds no syntax examples or edge-case guidance beyond what the schema 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?

The description states a specific verb and resource ("Get a company's firmographics") and names the accepted identifiers. It clearly distinguishes this tool from sibling person and school enrichment tools by focusing on company data.

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 implies when to use the tool by tying it to LinkedIn company URLs, slugs, or numeric IDs, but it does not explicitly say when to choose enrich_company over enrich_person, enrich_school, or search_people. No exclusions or alternatives are 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?

With no annotations, the description carries the full behavioral burden. It does disclose two useful traits beyond the schema: the call is metered ("1 credit") and it is conditional ("if found"), implying a possible not-found outcome. It says nothing about whether a failed lookup still costs credits, whether results are cached or how fresh they are, or what permissions/auth the call needs.

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 sentence with the action and the caller's input formats front-loaded, followed by the fields returned and the cost condition. No filler and nothing repeated from the schema.

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 lookup with no output schema, the description does the important work of enumerating the return payload so an agent knows what it will get back. The remaining gap is operational: no annotation coverage means auth requirements, error/not-found semantics, and rate limits are left undocumented.

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 there is exactly one parameter, whose description already lists the accepted forms ("LinkedIn URL, slug or numeric/profile ID"). The description restates those accepted input formats without adding constraints such as example formats, normalization rules, or what happens with a malformed identifier, so the 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 names a specific verb ("Get") and resource ("a person's professional profile") and enumerates the returned fields (name, headline, title, company, location, experience, education). The person-vs-company-vs-school split against enrich_company and enrich_school is implicit in the resource noun rather than stated, which keeps it just short of a 5.

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 when-to-use guidance: nothing says when to pick enrich_person over search_people, or what to do when the identifier is ambiguous. The only usage-adjacent signal is the cost line "1 credit if found," which hints at a paid lookup but does not define the alternative paths an agent should consider.

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?

No annotations are provided, so the description carries the full burden. It usefully discloses the billing behavior ('1 credit if found'), which implies no charge when nothing is found, but it does not state what is returned on a miss (error vs. empty result) or any rate limits or auth needs.

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 short sentences with no waste; the resource scope is front-loaded and the credit cost follows immediately. Nothing needs trimming or reordering.

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 simple one-parameter read tool with no output schema and no annotations, the description covers the accepted input forms and the cost model. The main remaining gap is the return payload shape and miss behavior, which is a minor omission at this complexity.

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 single 'identifier' parameter is already documented. The description restates the accepted identifier forms (LinkedIn URL, slug, numeric ID) without adding format examples or normalization rules beyond the schema, so the baseline of 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?

States a concrete verb ('Get') and a specific resource ('a school or university'), which distinguishes it from the sibling enrich_company and enrich_person tools by subject type. It does not explicitly name those siblings, but the resource noun makes the scope unambiguous.

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: use this when you have a LinkedIn school URL, slug, or numeric ID and need school data. There is no explicit statement of when not to use it, no mention of the alternative enrich tools, and no prerequisites such as authentication requirements.

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?

With no annotations, the description must carry behavioral disclosure. "Show" implies a non-mutating read and the description reveals the response covers credits and plan, but it says nothing about authentication/account scoping, rate limits, or whether the balance is currency-denominated or credit-denominated.

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 eight-word sentence with the primary resource (credits) front-loaded and zero filler. Nothing is padded and nothing essential is buried.

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 trivial zero-param read with no output schema, the description covers the essentials of what comes back, but leaves the return shape (units, currency, plan format) undefined since no output schema exists to compensate. Adequate but with a visible gap.

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 tool takes zero parameters and the schema is an empty object, so there is nothing for the description to disambiguate. Baseline 4 applies; the description correctly avoids inventing parameters that do not exist.

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?

"Show the account's remaining credits and plan" pairs a specific verb with two concrete resources (credits balance, plan), which is far more informative than the bare name get_balance. It does not explicitly differentiate from siblings, but the enrich_*/search_people/get_lookup set has no overlap, so misselection risk is low.

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 only implied: the description says what is returned but never states when to call it (e.g., before a paid operation to check quota) or any exclusions. For a zero-parameter read tool the implied usage is fairly unambiguous, but no explicit guidance is given.

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?

With no annotations, the description carries the full behavioral burden, and it does disclose that lookups can be in a pending state. It says nothing about what is returned while pending (error vs partial result), whether results expire, id lifetime, or rate limits on repeated polling — material gaps for an unannotated retrieval 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?

A single tight sentence with the action front-loaded and the qualifying condition in parentheses. No filler, though the parenthetical could be promoted to a proper clause for scannability.

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?

There is no output schema, no annotations, and no parameter documentation, so the description must explain the return shape and the pending-result lifecycle on its own — and it does neither. For an async-result retrieval tool an agent needs to know what 'pending' yields and how to obtain the id.

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 0%, so the schema only says 'id: string'. The description clarifies that the id refers to an earlier lookup, but not where that id comes from, its format, or what happens with an unknown/expired id, which is the key semantic gap for a single-parameter tool.

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 verb ('Fetch') and resource ('the result of an earlier lookup'), and scopes it to a lookup identified by id. It is distinguishable from the sibling enrich_* and search_* tools, though it never names the tool that actually creates the lookup being fetched.

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 one concrete usage condition — 'use it when a person lookup is still pending' — which implies a polling pattern. It does not explain when not to call it, what to do once the lookup completes, or which sibling initiates the lookup, so the guidance is partial rather than complete.

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?

With no annotations supplied, the description carries the full load and does disclose key behavior: a hard page cap of 10 results, cursor-based pagination, AND-combination of filters, and a concrete cost model ('1 credit per non-empty page' — notably free for empty pages). It omits auth requirements, rate limits, and whether filters are case-insensitive, which keeps it off 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?

Front-loaded with purpose, output shape, and next step, then the filter enumeration — every listed filter carries distinct information, so the density is earned. The single long run-on filter sentence is harder to scan than a bulleted list would be, 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 nested-object search tool with no output schema, the description covers the essentials an agent needs: result cardinality, result type, pagination token source, cost, and how filters compose. Minor gaps remain around result fields beyond the slug and filter value validation, but nothing critical to a successful call 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?

The schema documents only two params and reduces filters to 'At least one criterion', so the description supplies essentially all filter semantics — enumerating the twelve filter keys with their expected value shapes (arrays, {"any": [...]}, {"min","max"} pairs, slug-or-id for company). One flaw: it instructs 'Pass next_cursor' while the actual parameter is named 'cursor', a mismatch that could momentarily mislead an agent.

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 ('Find people by criteria') and immediately defines the output shape ('up to 10 LinkedIn slugs per page'), which separates it from the enrichment siblings. It also names enrich_person as the downstream step, so an agent can tell discovery from enrichment 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?

Gives clear context for use — search a population, then enrich each slug with enrich_person — and explains pagination via next_cursor. It stops short of saying when NOT to use it (e.g., when you already have a slug and want data) and does not mention get_lookup for filter value discovery, so it is clear but not exhaustive.

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