Learn: education articles and courses

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

Beyond the readOnly/idempotent/openWorld annotations, it discloses a material constraint: Agah Pedia and Academy only answer from an Iranian network. It also explains partial-failure semantics with source='all' (failing source returns {'error': ...}, the other still answers), truncation via max_chars, and that article text is third-party content.

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-loaded with purpose and workflow, then mode-specific detail, with no filler sentences. It is dense — several facts packed per sentence — but every clause carries operational information. Slightly tighter grouping by parameter would improve scannability.

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 an 8-parameter, no-required-parameter, no-output-schema tool, it covers the search/read workflow, per-mode outputs (courses give 'titles and links only'), source fallback, and the geo constraint. What is missing is return shape for article search results (fields to expect before using `ref`) and pagination limits, though the schema documents the latter.

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%, so the baseline is 3, but the description adds real meaning: `ref` type encodes the source (Mofid ids are numbers, Agah ids are slugs, so ref selects the source implicitly), and kind='categories' vs. kind='courses' are described by what they enumerate rather than just by enum name. Minor gap: no added guidance on `page`/`per_page` interaction.

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 and resource set ('Search the Mofid learning blog and Agah Pedia ... or read one article') and names the content domain (bourse, fund, option, gold explainers). The two modes — search vs. read one article — are stated explicitly, so an agent can tell this apart from the market-data siblings in the list.

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?

Gives concrete triggering examples ('what is ROE', 'how do gold ETFs work') and prescribes the call sequence: search first, then re-invoke with `ref` from a result. It also routes between the three `kind` modes, saying what each returns, which is exactly the when-to-use guidance an agent needs.

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