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

Annotations already declare a safe, idempotent, closed-world read, so the description need not restate that. It does add the useful behavioral detail of which fields are matched (title/abstract vs. name), but leaves out matching semantics (substring, fuzzy, ranking), result ordering, and the 25-item cap behavior.

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?

A single front-loaded sentence with no filler, and the searchable scope comes before the field-level detail. The only blemish is the "repos" wording, which introduces a naming mismatch with the schema's `tools` enum value.

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?

An output schema exists, so return-value description is not required, and the core scope statement is present. What is missing for a three-parameter multi-entity search is the choice between this tool and its siblings plus the meaning of `limit`/`kind` beyond the enum.

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 only 33% (only `query` is documented as "words to look for"), so the description must carry more weight. It does implicitly explain the `kind` dimension by listing the searchable entity types, though it says "repos" where the enum says "tools" and gives no meaning for `limit` or the default "all".

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 gives a specific verb ("Search") plus the resources searched (arXiv papers, companies, tools, repos) and the fields matched (title/abstract for papers, name for the rest). That is far more informative than the bare name/title, but it never distinguishes this tool from siblings such as latest_papers, company, or dev_tools.

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?

There is no guidance on when to reach for this tool versus the many sibling lookups (get_paper, get_tool, latest_papers, trending). It also never states that the `kind` parameter should be used to narrow scope or when to leave it at the default "all".

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