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

Annotations already declare readOnly/idempotent/non-destructive, so the description's added value is real: it discloses that experts are returned 'without their source', that a Last Price credential with routing read scope is required, that Forge must be switched on, and that an unclaimed workspace gets a 403. Those auth and failure-mode details go meaningfully beyond the annotation block.

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?

The core content is front-loaded, but the payload is delivered as one sprawling run-on sentence with deeply nested parentheticals, followed by four clipped fragments. Every clause carries information, yet the density and lack of paragraphing make it harder to parse than it needs to be for a read-only status call.

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 does the work of enumerating what comes back (models, data windows, drift frequency, ladder rungs, gate evidence, runs, experts minus source), and it covers the activation and credential preconditions. Only the relationship between returned collections and the loop/stage/limit filters is left unstated.

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% and both enums are already documented, so baseline 3 applies. The description does add conceptual framing that helps interpret the enums ('the rung it reached on the promotion ladder', 'self-recoding coder' vs the nightly training job), but it never mentions the `limit` parameter or how the filters compose.

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+resource ('Read Forge for your workspace') and enumerates the concrete payload: trained pricing models, promotion-ladder rungs with gate evidence, recent runs, and auto-written pricing experts. That is far more specific than the tool name alone and distinguishes it from mutation siblings like reject_forge_candidate and from get_learned_pricing, though it never names those siblings 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?

Usage context is implied rather than routed: 'Nothing here changes a price' and 'Not available until Forge is switched on' tell the agent this is a read-only status check gated on Forge being enabled, but no alternative tool is named for adjacent needs (e.g. rejecting a candidate, reading learned pricing). The prerequisites are clear; the when-vs-what-else guidance is absent.

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