Plan research scope

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

With no annotations, the description carries the full behavioral burden. It usefully discloses what the tool produces (targets plus kill criteria), but says nothing about whether it is read-only, whether it persists anything, or what the returned plan looks like structurally.

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?

One dense sentence, front-loaded with the core transformation and then the payoff (kill criteria). Every clause earns its place and nothing is padded.

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?

There is no output schema and no annotations, so the description is the only source of behavioral and return-value information. It hints at the plan's components but is thin for a tool whose entire value is the shape of the plan it emits.

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 100% for both parameters, so the schema already documents 'scope' and 'domain_hints' with examples. The description adds no syntax, format, or constraint detail beyond that, making the baseline 3 appropriate.

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 gives a specific verb+resource ('turn a research scope into a source-target plan') and enumerates the plan's contents (primary-source targets, corroborating targets, kill criteria). It is clearly distinct from fetch_and_score/build_report/check_report in substance, but it never names or contrasts those siblings, so the differentiation is implicit.

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?

There is no statement of when to use this tool versus the sibling tools, nor any prerequisites (e.g. 'call before fetch_and_score'). The only conditional language ('when to abandon the topic') describes the plan's content, not the tool's usage context.

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