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

Beyond the annotations (readOnly, idempotent, non-destructive, closed-world), the description adds a genuinely useful behavioral fact: the tool 'opens nothing by itself' and only returns step-by-step instructions, requiring a subsequent cotlet_browser_* session to actually perform the action. This is exactly the kind of side-effect disclosure annotations cannot express. It stops short of describing the shape or length of the returned instructions.

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 core disclosure is front-loaded and earns its place, but the final sentence about Instapaper's official REST API v2 and the absence of an MCP server (dated 'checked 17 Oct 2026') is tangential justification rather than operational information. The three sentences also mix three distinct topics – purpose, follow-up procedure, and API background – without clear separation.

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 carries the burden of explaining the return value, and it partly does ('screens, buttons, fields'). However, it leaves unclear whether the agent should call cotlet_browser_open/navigate first, and the read-vs-instruct ambiguity is unresolved, so an agent still has to guess at the handoff sequence.

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 and the baseline of 4 applies. The description correctly implies no inputs are needed by framing the call as a pure instructions lookup.

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 name and opening clause promise 'Read highlights in the user's own Instapaper account', but the second sentence reveals the tool actually 'Returns how to do it in Instapaper step by step (screens, buttons, fields) and opens nothing by itself' – i.e. it is an instruction/knowledge tool, not a data reader. That mismatch between the stated verb and the actual behavior forces the agent to reconcile two conflicting purposes. The resource (Instapaper highlights) is clear, but the operation is ambiguous.

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?

It does give a follow-up path: 'then do it with the cotlet_browser_* tools in the user's Instapaper Cloud Browser', which tells the agent what to do after this call. But it never says when to prefer this over native-looking siblings such as instapaper_fetch_article_text or instapaper_list_unread_articles, nor when not to use it. The closing note on Instapaper's REST API v2 and lack of an official MCP server is background trivia rather than routing guidance.

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