linkedin_add_project

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It fails to mention any side effects, such as whether adding a project overwrites existing ones, whether authentication is required (implied but not stated), or if the operation is idempotent. The agent receives no warning about potential destructive outcomes, which is critical for a write operation.

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 sentence, which is brief but excessive for an 8-parameter tool. It sacrifices necessary detail for the sake of brevity. The structure is front-loaded, but the content is insufficient for the tool's complexity, making it undercooked rather than concise.

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 8 parameters, no output schema, and no annotations, the description is severely incomplete. It does not explain parameter relationships, expected behavior (e.g., whether isCurrent affects endYear), or what the response looks like. An agent has insufficient information to invoke this tool 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 input schema has 8 parameters, but only 25% provide descriptions (name and url). The description adds no extra meaning for parameters like startYear, endMonth, or isCurrent. Given the low schema coverage, the description should compensate by explaining when to use these fields (e.g., 'For ongoing projects, set isCurrent'), but it does not. This leaves the agent guessing about parameter semantics.

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 action ('Add a project') and the target ('to the LinkedIn profile'). It effectively distinguishes this tool from siblings like 'linkedin_add_experience' or 'linkedin_add_education' by specifying 'project' as a separate entity. However, it does not elaborate on what constitutes a project on LinkedIn, which leaves minor ambiguity.

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 guidance on when to use this tool versus alternatives such as 'linkedin_add_experience' or 'linkedin_add_publication'. The description lacks context about prerequisites, whether projects are distinct from other sections, or situations where this tool is appropriate. This omission limits the agent's ability to choose correctly among many similar add tools.

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