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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds the genuinely load-bearing fact that the tool 'opens nothing by itself' — a caller who misses that would wrongly assume the note is created. It also explains why browser automation is required (the official OData API is read-only and admin-gated), which is useful context beyond the annotations.

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 and the 'returns instructions, does nothing itself' caveat are front-loaded in the first two sentences. The third sentence on MarketSharp's OData API is slightly tangential but earns its place by explaining why the browser path is necessary.

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 zero-parameter, no-output-schema tool, the description covers what is returned and the follow-up step well. It does not address how the agent should target a specific contact/job when the returned guide is generic, nor how the guide's scope relates to the user's account — a real gap for a note-adding workflow.

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 the schema-coverage baseline of 4 applies. The description does not need to explain argument syntax, though it leaves open how the target record or account is identified.

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 states a specific verb and resource ('Add note in the user's own MarketSharp account') and immediately clarifies the unusual mechanic: it 'Returns how to do it in MarketSharp step by step' rather than performing the write. It does not explicitly contrast with the sibling marketsharp_* tools, so an agent must infer whether those are API-backed operations while this one is a guide.

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 gives clear chaining guidance: call this to get screens/buttons/fields, then execute with the cotlet_browser_* tools in the MarketSharp Cloud Browser. What is missing is any exclusion or alternative — for example, when a generic guide tool (cotlet_app_guide) would suffice instead of this MarketSharp-specific one.

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