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

Annotations already declare readOnly=false, destructive=false and openWorld=false; the description adds the meaningful behavioral boundary that creation is inert (no research executed, no demand established) and that idempotencyKey makes retries safe, which resolves the apparent tension with idempotentHint=false. It omits visibility ('private' appears only in the title) and failure/side-effect details, but adds real value beyond the structured fields.

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?

Three short sentences, front-loaded with the action and then the two highest-value clarifications. No filler or restatement of the title.

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?

The output schema means return values needn't be described, and mutation safety is covered by annotations. But for a create tool with a nested, entirely undocumented profile object and 0% schema coverage, the description leaves the agent without enough information to populate the payload 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?

Schema description coverage is 0%, so the description carries the full burden, yet it only explains idempotencyKey and gestures vaguely at 'declared capabilities' for the nested profile object. The required `name` and every profile subfield (skills, capacity, industries, geographies, excludedActivities) and their constraints go unmentioned.

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 ('Save a research thesis workspace and declared capabilities') and immediately demarcates scope from the closely named sibling research_opportunity_workspace ('does not run research or establish demand'). An agent can distinguish this from get/list/update_opportunity_workspace and research_* tools without opening the schema.

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?

The exclusion 'does not run research or establish demand' implicitly routes agents to research_opportunity_workspace for actual research, and the retry line gives operational guidance. It stops short of naming the alternative explicitly or stating prerequisites (e.g. whether a thesis must exist first), so it's clear context without full when/when-not coverage.

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