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

Annotations already establish readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered; the description adds genuinely new behavioral context by disclosing the output shape (whose voice it writes in, which sections appear) and a grounding constraint: 'It invents no figure or quote.' That tells the agent the tool will not fabricate numbers, which is decision-relevant. It does not state length limits or what happens when inputs are sparse.

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 sentences, front-loaded with the purpose followed by inputs and outputs; there is no filler or marketing padding. The only mild inefficiency is the repeated 'you give / you get' construction, which is still readable and purposeful.

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 12-parameter generator with no output schema, the description does the needed work: it explains what the agent supplies, what it receives, and that grounding is enforced. The one gap is that only 4 of the 8 enum asset types are named, and it never clarifies that the remaining 10 parameters are optional and inferred when absent, leaving the agent to rely on the schema alone.

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%, so the baseline is 3. The description adds some meaning by grouping the inputs into a narrative (the asset, your solution, the customer's situation, the objections you expect) and by implying that the omitted optional fields are inferred from 'your words.' However, with 12 parameters it does not add semantics for fields like budget_context, urgency_drivers, competitive_context or champion_wins beyond what the schema already says.

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 uses a specific framing ('give your champion what they need to sell internally') and then concretely enumerates the deliverable types (executive brief, internal business case, objection responses, talking points), plus what comes back (recommendation, Q&A, decision requested, reader note, sector notes). It is clearly distinguishable from most siblings, though it does not acknowledge overlap with roi_business_case_builder despite supporting an 'internal_business_case' asset type.

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 implies the usage context (equipping a champion ahead of an internal sale) and lists the inputs it expects, which hints at when to reach for it. But it gives no explicit when-to-use/when-not guidance and never names the alternative tools for adjacent jobs such as roi_business_case_builder or proposal_section_writer, so the agent must infer selection.

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