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

With destructiveHint=false and openWorldHint=false already declared, the description adds real value by confirming "Changes no record" and by disclosing the critical non-obvious trait that a stored draft is never sent by the product — the founder copies it. It does not cover what happens on ID collision / versioning or what the response contains, but the annotations carry the safety profile.

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?

Front-loaded with the verb and resource, then the two behavioral constraints in short sentences. The long kind enumeration in the first sentence is bulky but earns its place by tying to the kind enum; there is otherwise no filler.

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, but for a single required nested object with many optional sub-fields and 0% schema coverage the description leaves the agent without guidance on which fields to populate or how versioning/review flags behave. Adequate to know what the tool is for, insufficient to invoke it confidently on the first try.

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% against a deeply nested artifact object with ~15 fields, so the description should compensate more than it does — fields like version, agentName, structured, draftFindings, reviewed and approvedAt are unexplained. It does partially help by mapping prose artifact names onto the kind enum (brief, draft, map, script, analysis, verdict table, briefing, report, risk brief, roster) and by implying relationshipId via "attached to a relationship or to the raise".

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?

States a specific verb and resource ("Stores an output … attached to a relationship or to the raise") and enumerates the concrete artifact kinds it accepts. An agent can tell this is the persistence path for generated fundraising deliverables, distinct from reading (fundraising_get_artifact) or approving (fundraising_approve_artifact), though it never names those siblings explicitly.

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?

Usage is only implied: the enumerated outputs (investor brief, unsent draft, intro map, pitch script…) suggest the situations that call for it, and "attached to a relationship or to the raise" implies the two scoping modes. There is no explicit when-to-use / when-not-to-use guidance and no pointers to alternative tools for comparison.

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