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

Annotations declare only a mutation-shaped safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false). The description adds substantial behavioral context beyond that: templates are private by default, owner-only sharing, teammates can read/use but not change a shared template, use never launches research, and save.requestId makes creation retry-safe. This is exactly the extra disclosure annotations cannot carry.

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 description is dense and multi-sentence, but it is front-loaded with the action set and follows a logical progression (purpose -> sharing -> contents -> method behavior -> use semantics -> revision/retry safety). Most sentences earn their place given the tool's complexity, though the template-adaptation passage is arguably more than an agent needs to select and invoke the tool.

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 complex, nested, five-parameter mutation tool with an output schema (so return values need not be explained), the description covers the critical behavioral and lifecycle concerns: sharing model, use-vs-research separation, revision requirements and retry safety. The main residual gap is per-field semantics for the configuration payload, which neither schema nor description fully addresses.

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 must compensate. It does add meaning for methodId (calculator-backed methods design their own tasks), for save.requestId (retry-safe creation), and for expectedRevision (required for update/use), plus sharing maps to isSharedWithTeam. However, name, goal, studyLocale, question response types, attachments, and templateId receive no semantic explanation, leaving much of a 5-parameter nested schema undocumented in both structured and prose form.

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 opening states a specific verb set (saves, updates, uses) and a precise resource (Custom research template), and immediately distinguishes itself from the delete sibling: 'Deleting one is a separate operation.' An agent can route correctly between manage_study_template and delete_study_template without opening either 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?

It enumerates the three actions (save/update/use) and gives conditions for each: updates and use require the current revision, and 'use' creates an independent editable draft that 'never starts research' and is finished in the web app. It also names the excluded operation (deletion) explicitly, so the agent knows what this tool will not do.

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