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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false and openWorldHint=false, so the agent knows this is a local, non-destructive, non-idempotent write. The description adds only 'persistent', which is a mild behavioral detail; it says nothing about duplicate-name behavior or what a project contains.

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?

A single short sentence with no filler, front-loading the verb and resource. Nothing is wasted or buried.

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 creation tool with two undocumented parameters, no output schema, and only partial annotation coverage, the definition is too thin. An agent gets no sense of what a project holds, how it relates to claims/evidence collections, or what happens if the name collides with an existing project.

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?

Two parameters exist with 0% schema description coverage, so the burden falls on the description, which says nothing about 'name' (naming rules, uniqueness) or 'description' (purpose, default of empty string). It fails to compensate for the coverage gap.

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 ('Create') and resource ('research project'), plus the qualifier 'persistent' which signals the project survives across sessions. It does not, however, distinguish itself from sibling creation tools like create_claim or create_evidence_collection, so sibling differentiation is left to the agent.

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?

No when-to-use guidance, no prerequisites, and no mention of alternatives such as checking list_projects first to avoid duplicates. The agent must infer the correct moment to call this from the name alone.

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