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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint, and the description adds substantial behavior beyond them: silent clamping of days/limit to tier caps, tier-gated field availability, the live/synced (not frozen snapshot) signal semantics, the no-gating on Stocklake's internal trading engine, the per-article fallback score path, and the deliberate absence of a separate news_score field. No contradiction with annotations; 'For informational purposes only' reinforces the read-only profile.

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 purpose is efficiently front-loaded, but the signal_score block is one dense, run-on paragraph with heavy nested parentheticals (last-90-days, shared resolver, internal-engine caveat, fallback path), making it hard to parse. Clamping and tier facts are also restated three times — in the days/limit text and again in the closing 'Free tier/Pro tier' summary — adding redundancy to an already long definition.

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?

For a genuinely complex tool (tier-dependent clamping, shared-signal freshness semantics, per-article fallback), nothing an agent needs to call it correctly is missing — edge cases like null-when-neither-path-produces-value are explicitly handled. Since an output schema exists, the extensive per-article field explanation is a bonus, though slightly over-explains what the schema could carry. Slight over-reach rather than under-specification.

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% — the days/limit descriptions in the schema already carry the exact clamping and tier-cap text the description repeats verbatim. The description adds the status enum ('ok'/'empty') and per-article field narrative, but those concern the return shape, which an output schema exists to cover. On parameters themselves the description is essentially duplicative, placing it at baseline.

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 opening line 'AI-analysed news for a stock, newest first' states a specific verb, resource, and distinctive qualifier. The qualifier 'AI-analysed' plus 'Only returns articles processed by our AI pipeline' cleanly separates it from a raw feed like get_news_feed, so an agent can disambiguate without opening other schemas.

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?

The description implies usage through the 'AI-analysed' framing and explains that signal_score/signal_score_band are the same values get_signals()/get_stock_research() report via a shared resolver, which orients the agent to data relationships. However, there is no explicit when/when-not routing — it never says 'use get_news_feed for raw articles' or 'use get_signals for standalone signal data.'

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