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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavior not in the schema: the free sample returns only the last twelve observations while a member key unlocks all of them, and the dossier is truncated to its public part without a key. That is real gating context, though error/not-found behavior and any rate limits go unstated.

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 entire description is a single run-on sentence built as a twelve-item comma list with no leading verb and no summary clause. The access-block clause is buried at the very end, and the enumeration of returned fields crowds out the access model, which is the one thing an agent most needs up front.

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 earn its keep by enumerating the response shape, which is the right thing to do here. But for a tool whose behavior differs materially by authentication state, it omits failure modes (unknown slug, expired key) and any routing guidance against the many sibling getters. Adequate, not complete.

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% (only 'key' is documented, 'slug' is bare), so the description needs to compensate and does so partially by explaining exactly what the key unlocks at the data level (twelve vs. all observations, partial vs. full dossier). The slug parameter's meaning is never discussed beyond its pattern. This is helpful but leaves the undocumented half thin.

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 returns the full signal object identified by slug, enumerating its sub-resources (series, observations, vectors, figures, hypotheses, organisations, dossier, offers, access block). It is specific about the resource, though it never states a verb and leans on an API path reference ('the same object as /api/atlas/<slug>') that an agent cannot resolve on its own. Sibling differentiation comes only implicitly, via the enumerated sub-objects that other tools like get_series and get_dossier also expose.

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?

There is no when-to-use guidance and no mention of any alternative tool, despite seven sibling getters that overlap with the sub-objects listed here. The only usage-like information is implicit: the key parameter selects free-sample versus member content. An agent must infer from the sibling names whether to call this or get_series/get_dossier directly.

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