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

The description adds genuinely non-obvious behavior beyond the annotations: 'opens nothing by itself' confirms the tool is a guidance generator, not an actuator, which matches readOnlyHint and prevents a costly misread of the action-oriented name. It also previews the return content (screens, buttons, fields). It says nothing about failure modes, auth expectations, or how current the guide is.

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?

Purpose, limitation, and handoff are packed into two dense sentences with no filler, and the limitation follows immediately after the action claim. The trailing official-API sentence with the '(checked 6 Nov 2026)' stamp is marginal and could be trimmed.

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 parameters and no output schema, the description must carry the full burden, and it largely does: it states it returns step-by-step instructions and promises no side effects. The remaining gap is the unexplained absence of any inputs, but the readOnly/idempotent/non-destructive annotations cover the safety profile.

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 zero properties, so the nominal baseline is 4, but the omission is surprising: an agent told to 'comment on post' expects to identify a target post and comment text. The description never explains that no inputs are accepted or that the guide is generic, leaving the agent to reconcile the mismatch itself.

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?

Names a specific verb and resource (comment on a LinkedIn post) and then clarifies the actual operation: it returns a step-by-step guide rather than performing the action. It also distinguishes itself from the cotlet_browser_* tools it hands off to. It does not, however, differentiate itself from the sibling linkedin_create_post, which by naming convention likely follows the same guide-then-browser pattern.

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 a clear workflow: call this first to get screens/buttons/fields, then execute with cotlet_browser_* in the user's LinkedIn Cloud Browser. The note about LinkedIn's official API requiring an approved application implicitly justifies choosing this path. There is no explicit when-not-to-use guidance, so it stops short of a 5.

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