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

Annotations already declare non-destructive and closed-world, but the description adds substantive behavior: every figure is validated against its own claim's source in the registry, and cross-document mismatches are surfaced by name. The no-side-effect statement reinforces the safety profile with domain-specific framing rather than restating annotations.

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 dense sentences with no filler, and the core action is front-loaded. The middle clause about the registry is somewhat convoluted ("one registry cannot produce two numbers") but earns its place by explaining the discrepancy behavior.

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?

An output schema exists, so return values need no explanation, and the annotations plus the no-side-effect sentence cover safety. However, for a moderately complex tool with six parameters (many undocumented) and nested slide/figure structures, the description leaves the agent without guidance on required vs optional inputs like relationshipId, tailoringNote, or proposedByAgent.

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 33% across six parameters including nested slide and figure objects. The description adds real meaning for two otherwise opaque fields (messageLine as one line per slide, claimRef as a registry claim reference), but says nothing about title, tailoringNote, relationshipId, proposedByAgent, or the grounded/screened/position/key fields.

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?

Specific verb + resource: "Draft a slide deck" with a defined shape (slide order, one message line per slide, figures citing the claims registry). It is clearly distinguishable from the sibling propose/approve tools (fundraising_propose_memo_version, fundraising_approve_deck_version) because it names drafting explicitly and scopes it to the deck.

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 final clause "Drafting approves nothing and sends nothing" situates the tool in the lifecycle (proposal precedes approval) and implicitly routes the agent to approve_deck_version for the next step. It stops short of naming alternatives or exclusions explicitly, so it does not reach a 5.

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