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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavioral context: which studies need a browser versus which run server-side via add_screenshot(page_url). It stops short of describing error behavior for an invalid playbook name.

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 opening sentence front-loads the verb, resource, and payload, and the long playbook list is necessary selection data rather than filler. It is dense, but the multi-line semicolon-heavy enumeration is heavier than ideal for a single paragraph.

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 output schema, the description carries the burden of saying what comes back ('the full text') and does so. Browser vs server-side requirements per playbook and the legacy alias ('positioning_pass' is the old name of 'website_teardown') round it out; only failure/edge handling for bad names is missing.

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 coverage is 100%, so the baseline is 3, but the description compensates for the absent enum on 'name' by listing the valid playbook identifiers. It also clarifies the optional 'url' is only needed if the target site is already known, adding meaning beyond the schema's terse 'if you already know it.'

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?

States a specific verb and resource ('Return the full text of a Cobalt study playbook') and then defines what a playbook actually is, distinguishing it from sibling tools like create_review or add_screenshot. The enumeration of playbook names gives the agent an unambiguous picture of what this tool yields.

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?

Each playbook variant is annotated with when it applies ('can a buyer tell what they would pay', 'judged as a first-time visitor', 'two or three products compared for one buying decision'), which effectively routes selection. It does not explicitly say when NOT to call this tool or how it relates to create_review (e.g., fetch then run), leaving that inference to the agent.

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