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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds ordering semantics (chronological), which is genuinely useful, but says nothing about how the limit interacts with that ordering, truncation behavior, or pagination.

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, front-loaded sentence with no filler; every element (scope, return content, ordering) carries 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?

An output schema exists, so return values need not be explained, and the annotations cover mutability. For a two-parameter read tool this is close to complete, with only the limit/ordering interaction left implicit.

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% and both parameters are documented, including that limit selects the most recent messages. The description's 'chronological order' clarifies the output ordering but does not resolve how 'most recent' filtering composes with chronological presentation. 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?

States a specific verb (get) and resource (one LinkedIn conversation) plus the payload (its messages in chronological order). It is clearly distinct from list_conversations and search_messages, though it does not name them explicitly.

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 single-conversation scope implies this is the drill-down after a list/search, but the description itself gives no explicit when-to-use or when-not-to-use guidance. The routing hint lives only in the conversation_id schema field ('From list_conversations or search_messages').

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 annotations already declare this as a read-only, idempotent, non-open-world operation, so the safety profile is covered. The description adds some context by saying it returns raw data rows from any LinkedIn domain, but it does not discuss pagination, data scope, or other behavioral limits beyond what the schema and annotations already provide.

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 front-loaded sentence with no filler. It communicates the core action and example resources efficiently.

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 simple three-parameter read-only operation, full schema coverage, output schema, and clear annotations, the description is largely complete. It could be improved by explicitly mentioning the dependency on list_data_domains, but that gap is minor and partially covered by 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 100%, so every parameter is already documented in the input schema, which sets the baseline at 3. The description reinforces valid domain examples like POSITIONS and SKILLS but does not add syntax or meaning beyond the schema for domain, limit, or offset.

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: retrieving raw data rows from a LinkedIn data domain, with concrete examples like POSITIONS and SKILLS. It does not explicitly differentiate this from the sibling list_data_domains, but the contrast between raw data rows and domain listing is reasonably clear.

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 by the statement that this gets raw rows from any data domain, and the examples suggest valid domain values. However, it does not explicitly say when to use this versus list_data_domains or other sibling tools, nor does it state that the domain must first be discovered via list_data_domains.

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 openWorldHint=false, so the safety and side-effect profile is fully covered. The description adds only the field inventory, which is arguably duplicated by the output schema. It does not clarify whose profile (authenticated user vs. arbitrary member) beyond the vague "the user's".

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 zero filler, and the resource identification is front-loaded before the field list. Every word earns its place; nothing is repeated or 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?

With a rich annotation set, a full output schema, and no parameters, the description covers what an agent needs to select this tool. The remaining gap is the ambiguity of "the user's" — nothing tells the agent this is the authenticated user's profile as opposed to a lookup keyed by an identifier.

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, so there are no parameter semantics to explain; baseline for zero-param tools is 4. The description's field list is a reasonable substitute for explaining what comes back, though it is largely redundant with the existing output 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 pairs a specific verb ("Get") with a specific resource ("the user's basic LinkedIn profile") and enumerates the fields returned (name, headline, summary, location). It is unambiguous about what the tool retrieves; the small deduction is because it does not explicitly distinguish scope from siblings, though no sibling overlaps as a profile getter.

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?

No explicit when-to-use or when-not-to-use guidance, and no alternatives are named. Usage is only implied by the resource name, which happens to be sufficient here because no sibling tool returns profile data. An agent must still infer that this returns the authenticated user's own profile rather than a given member's.

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 cover safety (readOnly, idempotent, closed-world), so the description earns credit for adding the non-obvious constraints: results are capped to the consent window of the last 28 days and returned newest-first. The epoch-millisecond time format also preempts a common misinterpretation. It stops short of explaining pagination behaviour or whether the 28-day cap truncates offset paging.

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, zero filler, with the scope and ordering constraint front-loaded before the event-type enumeration. Every clause carries information the agent needs to call it correctly.

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?

Output schema and annotations are present and the parameter schema is fully documented, so the description only needs to supply the temporal scope and ordering, which it does. The one residual gap is how the 28-day cap interacts with limit/offset paging for an agent trying to page back further.

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%, including an explicit warning that resource_name values are undocumented — so the schema does the heavy lifting and the baseline of 3 is met. The description's 'newest first' framing does add ordering semantics that bear directly on how limit/offset behave, slightly above baseline.

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 the user's LinkedIn activity') and enumerates the four event types covered plus the 28-day scope and newest-first ordering. It does not name the siblings it differs from (list_posts, search_messages), so an agent must infer how this aggregated feed relates to those narrower 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 'since consent (last 28 days)' framing implies this is the cross-cutting recent-feed view, but no explicit when-to-use/when-not or alternative routing is given despite obvious siblings like list_posts and search_messages. Usage is inferable rather than 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?

Annotations already declare readOnlyHint, idempotentHint and a closed world, so the safety profile is covered. The description adds real behavioral value in stating the result ordering (most recently active first), which is not derivable from the schema. It says nothing about pagination semantics or total counts beyond what limit/offset already imply.

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 front-loaded sentence that conveys resource, identity and ordering with no filler. It is appropriately short for a simple list tool.

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 and full parameter documentation in the schema, plus annotations covering safety, the description covers what is needed to call the tool correctly. Minor gap: no hint about paging through results or what a default listing contains.

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 every parameter (limit, since, folder, participant, offset) is already documented in the schema and the baseline is 3. The description adds no syntax, format, or matching-behavior detail (e.g. how 'participant' text matching works) beyond 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?

States a specific verb and resource ('List LinkedIn message conversations') plus the sort order ('most recently active first'), which an agent can use immediately. It does not explicitly distinguish itself from get_conversation or search_messages, but the plural/list framing makes the distinction inferable.

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 when-to-use or when-not-to-use guidance, and no mention of the siblings (search_messages, get_conversation) that an agent would otherwise have to disambiguate against. The only directional hint is the default recency ordering, which is implicit rather than stated as a selection criterion.

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 discloses a real behavioral trait beyond the annotations: the first call is a full fetch and takes several seconds, warning the agent about latency and a cold-cache penalty. Annotations already cover read-only/idempotent/non-open-world semantics, and the output schema covers return shape, so this performance note is the additive value.

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, front-loaded with the purpose and finish with the latency caveat; nothing is wasted or 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?

With no params, an output schema, and read-only annotations, the description only needs purpose, scope, and any call-shape caveats, all of which it delivers. It could be slightly more complete by pointing to get_data_domain as the drill-down step, but nothing required for a correct 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 tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a no-param tool applies. No schema semantics are repeated or contradicted.

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 (List) and resource (LinkedIn data domains) and adds scope ('that have data for the user') plus what the result carries ('with row counts'). The plural/aggregate framing implicitly separates it from the singular sibling get_data_domain, though it never names that sibling explicitly.

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 line 'The first call fetches all data' hints that this is the discovery entry point and should be called before drilling into a domain, but it never explicitly says when to use this versus get_data_domain or what the follow-up is. Usage is implied rather than 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, so safety is covered. The description adds two things not in the annotations: the default ordering (newest first) and a data-visibility constraint tied to consent that determines which posts this tool can even return.

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, front-loaded with the core purpose and followed by the caveat. The consent sentence is slightly awkwardly worded ('after the user's consent'), 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?

With an output schema present and full parameter documentation in the schema, the description needn't explain return values. It covers purpose, ordering, and the visibility caveat; only a note on pagination behavior or whether results are scoped strictly to the authenticated user 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%, with limit, query, since, and offset all documented in the schema, so the baseline is 3. The description's 'newest first' implies the sort order the offset/limit operate over but adds no syntax or format detail 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 ('List the user's LinkedIn posts') plus a result ordering ('newest first'), and explicitly names the sibling that owns a subset of the data (get_recent_activity). An agent can distinguish this from the other list/search siblings without opening a 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?

Provides an explicit when-not rule: posts made after the user's consent may only appear in get_recent_activity, which routes the agent to the right alternative. It stops short of covering the broader choice against search_messages/search_connections, but the key exclusion is 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?

Annotations already declare readOnly, idempotent, and non-open-world behavior, so the description doesn't need to cover safety. It adds genuine value beyond that with the result ordering and the caveat that email addresses are only returned for connections who permit exporting — a data-availability trait an agent cannot learn 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?

Two short sentences, front-loaded with the verb and scope, followed by the one non-obvious caveat. Nothing is redundant or 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?

With an output schema, full parameter coverage, and read-only annotations, most of the burden is lifted. The description covers scope, ordering, and the email-permission caveat; a note on pagination expectations or an explicit 'use X instead for profiles' pointer would complete it.

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 description adds no parameter detail beyond what is in the schema (limit, query, company, connected_since are all self-documented). Baseline 3 applies since 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?

States a specific verb (search) and resource (the user's first-degree LinkedIn connections), plus the ordering ('most recent first') and a scope qualifier (first-degree only). No sibling tool touches connections, so there is no ambiguity to resolve.

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 by the tool name and the 'first-degree connections' scope, but the description never says when to reach for this versus alternatives like get_profile or search_messages, nor any prerequisites. An agent must infer that it should use this only when looking for a connection list.

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, and closed-world, so safety is covered. The description usefully adds result ordering (newest first) and matching semantics (case- and accent-insensitive), but says nothing about pagination behavior or what happens with no filters applied.

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, zero filler, with the identifying verb and resource front-loaded and the ordering caveat second. Everything present earns its place.

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 needn't be explained, but for a search tool with seven optional filters an agent would benefit from knowing default behavior with no query and how it relates to the listing siblings. Adequate but with a clear routing 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?

Schema description coverage is 100%, so all seven parameters are already documented with defaults and bounds. The description's note about case/accent-insensitive matching slightly enriches the query/sender params, but adds little 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 ("Search LinkedIn messages") plus an ordering guarantee. It does not differentiate itself from the sibling list_conversations/get_conversation, so an agent must infer the boundary between 'search' and 'list'.

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?

No guidance on when to use this versus list_conversations or get_conversation, and no mention of behavior when query is null (does it return everything?). Usage must be inferred from the name alone.

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