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

Annotations already declare readOnly/non-destructive/closed-world, and the description adds substantial context beyond them: what is returned (projects, published equity shares, capacity by stage and technology, attributable capacity, recent change-ledger entries) and an aggregation caveat that stage totals count each project's whole capacity and must never be summed across companies. It also discloses the alias-normalization behavior (EDF/EDF Renewables, SAPCO/Aramco Power) and the separate `coverage` block that is excluded from stage totals.

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 purpose and key are front-loaded in the first clause, and nearly every sentence carries operational information (return shape, alias rules, aggregation warning, coverage scope). It is dense and parenthetical-heavy with some rambling punctuation, which slightly slows parsing of the return-shape information buried mid-paragraph.

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?

There is no output schema, so the description must carry the return-shape burden, and it does: it describes project lists, per-stage and per-technology capacity, attributable capacity, change-ledger entries, and the separate coverage block. For a single-parameter lookup tool, an agent has everything needed to call it and interpret the result.

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% and the schema already documents the single `company` parameter, so the baseline is 3. The description earns above baseline by enumerating additional slug examples and, more importantly, by explaining that alternative spellings of the same company resolve to one entity and that a published name is accepted, which changes how an agent should populate the field.

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?

Identifies a specific resource (one developer or shareholder), the exact dataset it lives in (Saudi Renewables Tracker), and the key used to address it (the page slug), with concrete slug examples. It also distinguishes itself from search_projects by noting that tool returns developers as published, so an agent can tell the two apart without opening either schema.

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 clear context for use: look up a single company by slug or published name, and it explicitly extends coverage to companies that appear only in the coverage lists (ENGIE, TAQA, DEWA), which prevents an agent from wrongly assuming a miss. It stops short of explicit when-not guidance or a named alternative for bulk company discovery, so it is strong but not complete routing guidance.

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