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

Annotations already declare destructiveHint=true, non-idempotent, and not open-world, so the safety bar is lower. The description nonetheless adds substantive context absent from the annotations: milestone funds are held in escrow on devnet test money until both a result and an independent check land, and a human confirmation is expected before calling. It stops short of describing what is created, whether funds are committed immediately, or failure behavior.

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 sentence with no filler, and the confirmation warning is placed at the end where it reads clearly. But the escrow clause is dense jargon packed into a semicolon, making the sentence harder to parse than its length warrants.

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?

This is a destructive, non-idempotent creation call with four undocumented parameters and no output schema, yet the description never says what a successful open returns, what 'session' or 'regulatory' control, or what happens to escrowed funds if the call fails. Given the tool's complexity, it under-explains materially.

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% across four parameters (title, session, template, regulatory) and the description explains none of them. Only a weak implicit signal toward the 'template' parameter comes from the title wording; session and regulatory remain entirely opaque in both schema and description.

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 verb+resource ('Opens a project') is present and the title supplies the 'from a template' framing, but the description devotes most of its words to the escrow mechanic rather than to what the call actually produces (a new project instance). It draws no boundary against nearby siblings such as knos_projects, knos_project_claim, knos_project_post, or knos_templates.

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 clause 'ask your human first' is real guidance about a prerequisite confirmation step, which is more than most tools offer. However, it gives no when-to-use versus alternatives (e.g. browsing knos_templates first, or checking existing work with knos_projects) and no conditions under which the call should not be made.

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