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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered elsewhere. The description goes beyond by documenting the exact return shape ({projects:[...], total, generated_at}) and adding synonym context ('under construction', 'come online') that helps a model map user phrasing to this tool rather than a sibling.

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?

It's a long paragraph, but every sentence earns its place. The structure front-loads the core use case and example before diving into parameters, and distinct logical blocks (purpose, params, return, exclusions) are present. The only reason it's not a 5 is that the parameter documentation could have been left to the schema (which covers it) to make the description more skimmable, but the compression is still strong.

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 read-only pipeline tool with an output schema present, it covers all the bases: parameter list, return contract, exclusions, and pagination via limit/offset. It could theoretically add details on default sort order or maximum date ranges for expected_completion_before, but those are minor given the output schema fills the gap. Feels complete for its purpose.

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. The description earns the extra point by listing the fixed status enum inline, giving concrete example values for operator ('Equinix', 'Digital Realty'), clarifying ISO-2 format for country, and explaining the expected_completion_before date format. This compensates for the fact that the schema itself does not define enums and saves the model a trial-and-error call.

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 opens with a specific verb+resource ('what is being built / announced / permitted') and clearly frames get_pipeline as the 'forward-looking construction pipeline.' It proactively differentiates from siblings by stating what it is not (no `market` param, use search_facilities for a named market), leaving no ambiguity about its scope.

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?

It gives an explicit 'Use when' rule, a full worked example with status=construction, and then explicit 'Do NOT use' guidance for operational facilities (search_facilities) and M&A deal flow (list_transactions). This is the gold standard for routing an agent to the correct tool.

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