person.work — Agent-maintained CV

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the read-only nature is covered. The description adds some context about the data being 'canonical' and containing 'stable experience identifiers and confirmed facts,' which is helpful but not extensive. It does not discuss response format, pagination, or other behaviors, so the added value is modest.

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 two concise sentences, with the primary function front-loaded and the usage guidance following. Every sentence adds value without redundancy or 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?

With no output schema, the description should convey what the return value represents. It does so by stating it returns the 'canonical record' and hints at its content ('stable experience identifiers and confirmed facts'). While it doesn't enumerate fields, this is likely sufficient for a no-parameter read operation, and the agent can infer the structure from the description.

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 has zero parameters, so the baseline is 4. The description does not need to explain parameters, and since there are none, it correctly adds nothing. The schema coverage is vacuously 100%, and the description does not introduce any confusion.

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 states a verb ('Returns') and a specific resource ('the OAuth-authenticated owner's canonical record'). It also gives a hint of its purpose ('preserving stable experience identifiers and confirmed facts'), which distinguishes it from siblings like get_profile or propose_my_career_change, though it does not explicitly name 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?

The description provides a clear usage context: 'Read this before proposing an ongoing CV update.' This tells the agent when to call it, but it does not mention when not to use it or point to alternatives, so it lacks explicit 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 already declare readOnlyHint=true, so the description adds value by noting contact values are excluded and that the record is public and opt-in. However, it does not disclose other behavioral aspects like pagination, error conditions for missing or non-public records, or the structure of the returned object.

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 very concise, two sentences with no filler. It front-loads the key constraint (public, opt-in) and the contact exclusion. However, it omits critical parameter details and usage context, making it efficient but incomplete.

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 tool with three parameters and no output schema, the description is insufficiently complete. It does not explain what 'full' vs 'summary' formats mean, what include_extensions does, or what a Career Record contains. It also fails to differentiate from siblings, leaving an agent without enough information 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 description coverage is only 33% (only username is documented). The description does not mention the format or include_extensions parameters, and it does not explain their meaning or default behavior. It adds no parameter-level context beyond the schema, which is inadequate given the low 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 clearly states the tool returns a public Career Record and specifies the opt-in condition and contact exclusion. However, it does not differentiate from sibling get_my_career_record, which likely serves the same resource type but for the caller's own record.

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 tool versus alternatives. It does not mention that get_my_career_record should be used for the caller's own record, nor does it describe any prerequisites like whether the target user must have enabled MCP visibility (it does imply that, but not as a usage guideline).

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?

Discloses important side effects: it creates a review item, imports protected copies only after owner approval, and cannot directly apply or publish. It does not describe every possible effect, but the key behavioral boundaries are clear.

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 brief and front-loaded with the main purpose. Every sentence adds meaningful information, with no redundant or filler 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 complex nested schema and no output schema, the description provides good high-level context but not enough to construct a valid patch or instruction without closely inspecting the schema. Sibling tool names help, but the description does not explain how this tool fits with them in detail.

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 description hints at 'structured diff' and logo handling but leaves the instruction and proposed_patch parameters largely to the schema. Some nested fields have descriptions, but the overall parameter semantics are not fully explained in the tool description.

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?

Clearly states the tool adds a structured, human-readable diff to the owner's review inbox, and explicitly contrasts with applying or publishing changes. This makes the core purpose and non-purpose 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?

Provides explicit usage context: use for normal maintenance after the initial import, not for applying or publishing. However, it does not name sibling tools to directly guide selection among get_my_career_record, get_profile, or sync_my_profile.

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 meaningful behavioral context beyond the annotations: it states the operation is 'deterministically validates the payload and atomically creates a private profile when needed or replaces the owner's profile facts and complete experience list,' which aligns with the destructive and idempotent hints. It also discloses that 'person.work does not run a second AI interpretation' and that logos are 'imported a protected copy.' These details go beyond what annotations alone 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?

The description is a single paragraph of about six sentences, each contributing a distinct point: the operation type, exclusions, validation behavior, logo handling, identity requirement, and usage caution. It front-loads the primary purpose and uses clear, direct language. There is minimal redundancy, though it could be tightened slightly without losing 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 complex operation with nested objects, no output schema, and annotations that are not self-explanatory, the description covers the essential aspects: what it does, what it rejects, creation vs. replacement, logo handling, identity conditions, and a strong usage warning. It does not describe the response format or error scenarios, but given the operation's nature and the absence of an output schema, the provided context is sufficient for an agent to invoke 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?

The schema has 50% description coverage, and the description adds value for some key parameters: it explains the null-vs-omit semantics for company_logo_url and avatar_url, and clarifies that identity is only for first creation. However, it does not elaborate on many other fields (e.g., competencies, extension fields), which are left to the schema. Since coverage is moderate, the description partially compensates but not exhaustively.

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 'Explicit initial-import operation for structured facts already interpreted by the calling agent,' which precisely states the verb (import), the resource (structured CV facts), and the scope (initial import only). It also explicitly negates what it does not do ('does not accept or store a raw CV, PDF, or source text'), and the title reinforces the action. This clearly distinguishes it from sibling get and propose 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 explicit usage guidance: 'Never use this for routine updates' tells the agent when not to use it, and 'Identity is required only for first creation' sets a condition. It implies this is for initial import rather than updates, which differentiates it from propose_my_career_change, though it does not name the alternative explicitly. The 'initial-import operation' label provides clear context.

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