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

With no annotations, the description fully discloses key behavioral variations: public keys get anonymized versions (details stripped/withheld), internal keys get full named studies. It also explains the failure mode for customer-name search on public keys. This is rich, useful disclosure beyond what annotations would provide.

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 description is three sentences, front-loaded with the core purpose, and every sentence adds essential information: what the tool returns, key-dependent behavior, and how to search. No fluff or repetition.

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?

The description covers purpose, behavior, and search strategy, making it adequate for an agent to select and invoke the tool. However, it does not describe the return format (e.g., list vs full text, metadata), which would be useful given there is no output schema. Still, the stated content is sufficient for most cases.

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?

Although the schema already documents both parameters with 100% coverage, the description adds practical query examples ('fintech Salesforce migration', 'CPQ replacement') and a negative example (customer names don't work). This meaningfully extends schema guidance, especially for the query parameter.

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: 'Retrieve LeanScale customer case studies', clarifying the scope (problem and solution). This distinguishes it from siblings like get_benchmark or search_podcast by clearly stating it is about case studies.

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?

Provides clear search context: 'Search by sector, the kind of engagement, or the systems involved' and a critical caveat that customer-name search won't work on public keys. However, it does not explicitly mention when to prefer this tool over alternatives like search_leanscale.

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