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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, yet the description still adds real behavioral context: translation projects (baseLangProjectId set) permit only workflow field edits, and publications are auto-generated read-only copies whose changes are lost on regeneration. That is non-obvious, actionable mutability information beyond structured fields.

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 purpose, then field documentation, then caveats, which is the right ordering. The field enumeration is long but earns its place given no output schema; the one marginal sentence is the note that project IDs are unique across the portal.

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?

With zero parameters, no output schema, and simple read-only annotations, the main missing pieces would be return shape and mutability of results — both are covered in detail. Nothing an agent needs to call this correctly appears to be absent.

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?

The tool takes no parameters, so the baseline is 4. The description instead enumerates the returned fields and their formats (url with protocol/domain, parentId null vs project ID, visibility enum, ISO timestamps), which compensates for the absent output schema rather than duplicating a parameter schema.

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?

Opens with a specific verb and resource: "Lists all projects and publications in the portal available to the current user." It also notes the scope (current user) and distinguishes the returned types (Project/Publication), and explicitly routes to get_project for project-level modifiedOn, so an agent can separate it from single-project siblings.

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?

Clear context for use: enumerate everything visible to the user, and it explicitly says to use get_project when modifiedOn is needed for a non-publication project. It does not address when to prefer alternatives like search_portal or list_topics, so exclusions are incomplete rather than absent.

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