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

Beyond the read-only/idempotent annotations it discloses non-obvious semantics that would otherwise mislead: percent 100 means 'nothing outstanding, not everything succeeded', etaSeconds is null until something finishes, and analysis runs automatically when media is connected. This is exactly the kind of surprise-prevention an agent needs.

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-loads the purpose in the first clause and each subsequent clause carries distinct information (percent caveat, failed list, field inventory, polling loop). Dense but somewhat cramped with parentheticals and capitalization emphasis; still no wasted sentences.

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?

No output schema exists, so the description carries the return-value burden and does so thoroughly — percent semantics, failed items, done/total/pending counts, runningItem shape, etaSeconds, blockedOnModels, models. An agent has everything needed to poll and interpret results correctly.

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 100% and both parameters (token, projectId) are documented in-schema, so the description adds nothing about parameters. Baseline 3 applies.

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 exactly what it reports: 'How far the project's media analysis has got', with the key clarification that analysis is automatic rather than triggered by this call. It does not explicitly distinguish itself from the sibling get_job_status, but the media-analysis framing is specific enough to identify the resource.

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?

'Poll this while you wait' gives the usage pattern directly, and it routes to two alternatives by condition: request_ai_models when blockedOnModels > 0, retry_analysis for a failed item. Missing only a contrast with get_job_status, the other status-polling sibling.

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