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

With no annotations, the description carries the full burden and does so well: it discloses the asynchronous job model, typical completion time, quota cost (1 monthly plan unit plus 1 MCP action against a dedicated cap), that retrieval is free, and a non-obvious semantic caveat (difficulty is the Google Ads competition index 0-100, NOT SEO difficulty). This is exactly the kind of behavioral context annotations could not supply.

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?

Dense but front-loaded: the async job contract comes first, then mode semantics, then quota warnings. Every clause carries information (latency, quota, difficulty definition). It is a single long paragraph rather than structured sections, which slightly hurts scannability, but there is little filler.

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 10-parameter, no-annotation, no-output-schema tool, the description covers the essentials: what comes back (volume, CPC, intent, difficulty), the two-call lifecycle, cost model, and per-mode parameter requirements. Minor gaps remain around organization_id and the multi-tenant scoping, but nothing that would cause an incorrect invocation.

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 70%, and the description adds real meaning beyond it by mapping mode values to their required inputs (related needs seed, list needs keywords, domain/gap need domain, gap also needs competitor). It also explains that project_id marks keywords already being tracked. It leaves organization_id and the language/location defaults to the schema, which is acceptable at this coverage level.

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?

States a specific verb+resource ('Avvia una ricerca keyword') and explicitly describes the async contract (returns a job_id, re-invoke with job_id for results). It also enumerates the four research modes, giving an agent a clear picture of what the tool does. It does not, however, differentiate itself from siblings such as get_keyword_gap or get_keywords, whose capabilities overlap with the 'gap' mode, so it falls short of a 5.

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 strong operational guidance: the two-step job_id retrieval pattern, expected latency ('un paio di minuti'), the meaning of project_id, and the fact that retrieval does not consume quota. It names get_usage as the place to check remaining credits. What it lacks is explicit routing against siblings (e.g. when to prefer get_keyword_gap over mode=gap), so no exclusions are stated.

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