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

Annotations already declare a safe, idempotent, read-only operation, so the description does not need to restate safety. It instead adds substantive behavior: a key-gated paywall/member tier, an explicit inventory of what the free preview contains, and an explicit inventory of what the keyed response adds. What is missing is failure behavior (invalid or expired key, unknown slug) and whether the preview is truncated rather than filtered.

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 sentences, no filler, and the key/no-key branching is established before the field inventories. The long enumerations are dense but justified because there is no output schema to carry them. The clipped fragment opener 'The dossier.' costs a little front-loading clarity.

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 only two parameters, no nested objects, and no output schema, the description's field inventories are the right completeness investment. It adequately covers what an agent needs to call the tool and interpret the response shape. It stops short on error and edge cases – expired key, unknown slug, or whether counts are exact – which leaves a small gap for a tool whose main risk is misreading a partial preview as the whole dossier.

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 50% – the key parameter is documented in the schema, whereas slug is not – so the description carries part of the burden. It strengthens key's meaning by tying its presence to the preview/full branch, which is the single most consequential decision in the call. It says nothing about slug beyond the schema's pattern, so an agent gets no help if a slug lookup fails.

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?

The description makes clear this retrieves a 'dossier' for a signal and 'opens the complete dossier' when a key is present, so the resource and effect are identifiable. It never states which verb applies in the first sentence (the opening is the fragment 'The dossier.') and never distinguishes itself from get_signal, so an agent must infer the difference from the sibling name alone.

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 is only implied through the access-mode split: 'Without a key, a preview' versus 'A member key opens the complete dossier', which tells an agent which parameter configuration yields which scope. There is no guidance on when to call this instead of get_signal or get_edition, and no mention of what to do when the preview proves insufficient.

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