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

Annotations already declare a non-read-only, non-destructive, closed-world write, so the safety profile is covered. The description adds one genuine behavioral fact beyond that — it only links an existing report and performs no generation — but says nothing about idempotency, what happens on re-attach, permission requirements, or failure modes.

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?

Two tight sentences with the core action front-loaded and the constraint trailing, with no filler. Brevity tips into under-specification, but nothing in the text is wasted.

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?

Three required parameters at 0% schema coverage, no output schema, and no explanation of prospect_session_id or the resulting state of the workspace make this inadequate for an agent to call correctly without guessing. The description should at minimum identify what each required identifier refers to.

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%, so the description must carry parameter meaning and largely fails. 'Your own saved report' and 'user-chosen workspace' loosely map to report_id and workspace, but the required prospect_session_id is never mentioned and no UUID/format or validity constraints are explained.

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 (attach) and resource (a saved report) with the destination (user-chosen workspace), which is far more precise than the opaque 'glowup' name. The 'Does not build' clause implicitly separates it from glowup_start/glowup_build_open, though no sibling is named 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?

'Does not build' implies a usage boundary (use a build/start tool when you need generation), but the description never states when to choose this over glowup_start or glowups_get. The reader must infer the alternative from a negation rather than being routed to it.

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