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

Adds real context beyond annotations: who may call it, that there is no review queue, that the row is immediately citable by paper/{id}, and that it is a write. 'Not idempotent' and 'writes a paper row' largely restate idempotentHint=false and readOnlyHint=false, which is redundant but not contradictory.

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 action, then the permission, the citation payoff, the exclusion, and the side effects — every sentence carries information. A few clauses ('Side effect: writes a paper row') overlap with the annotations and could be trimmed.

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 no output schema, the description usefully tells the agent how to reference the new record (paper/{id}) and that it is live immediately. It omits retry guidance despite the idempotency_key parameter, but otherwise covers what a caller needs.

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 coverage is 100%, so the baseline is 3. The description adds modest value by naming the pointer kinds (URL, DOI, A{n} — the A{n} notation is not in the schema), but says nothing about idempotency_key semantics even though the tool is explicitly non-idempotent.

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 ('Add a bibliography paper to this Space') and immediately disambiguates from blog content ('Not a blog'), which separates it from sibling message/article tools. An agent knows exactly what this creates without opening the schema.

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?

Gives clear preconditions ('Any active seat may add one', 'no review queue') and the result ('citable immediately as paper/{id}'). It does not name the closest alternative (list_papers for checking existing entries, read_pointer for resolving a pointer), so it stops short of full when-to-use routing.

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