read_account_data

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

No annotations exist, so the description carries the full behavioral burden. It does hint that some data kinds may not be available for a given provider ('when supported'), but it says nothing about authentication requirements, what happens when an unsupported kind is requested, whether recruiter-message summaries need elevated permissions, or whether the call is purely read-only. For a multi-provider account read with zero annotation coverage, this is a substantial gap.

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 the verb first and the resource list after; no preamble or filler. The enumeration is long but each item corresponds to a real capability, so it earns its space. Slight redundancy with the `kind` enum keeps it from a 5.

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 two required enum parameters, no output schema and no annotations, an agent can construct a call but cannot predict the response shape, error behavior for unsupported kinds, or auth prerequisites. The description covers the 'what' adequately but not the operational context a multi-provider read tool needs.

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 0%, but both parameters are enum-constrained and self-describing, and the description enumerates the `kind` values in prose. The critical semantic gap is the provider × kind matrix: the description never states which kinds are valid for LinkedIn versus Naukri, leaving 'when supported' as an unresolved ambiguity the schema cannot answer. Partial compensation, hence a 3.

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 verb ('Read') and enumerates the exact resources available (profile, resume, skills, experience, education, preferences, visibility settings, jobs, applications, recruiter messages), which maps cleanly onto the `kind` enum. An agent can tell this is the read-side tool versus the many `preview_*`/`execute_confirmed_mutation` siblings. It never names a sibling explicitly, so it falls 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 when-to-use guidance: nothing says to check `discover_provider_capabilities` or `get_browser_auth_status` first, nor that writes should go through the `preview_*` tools. The only conditional is the trailing 'when supported', which is never defined. Usage is left entirely to inference from the tool name.

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