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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the read-only nature is covered. The description adds behavioral detail beyond that: it reveals that the response carries person_slug / company_slug for linked entities, and it explains that the output_format changes the serialization, noting that the JSON shape is 'larger and noisier for an LLM to read.' These are genuine behavioral disclosures not present in the annotations or schema, though it stops short of describing error conditions or response envelope.

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 front-loaded with the core purpose in the first sentence, followed by use-case and routing guidance. The second paragraph earns its place by explaining when to prefer sibling tools and the downstream consumers of entity slugs. It is slightly longer than necessary but contains no filler; the structure flows logically from what → when → alternatives.

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?

With no output schema, the description compensates by naming the returned fields (name, kind, description, Wikipedia link) and the presence of person_slug/company_slug for linked entities. It also covers the two parameters, the source of valid slugs, and the appropriate output format. For a simple read-by-slug tool, this is sufficient; an agent has enough to invoke it correctly and interpret the result, though it leaves response envelope details unspecified.

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, but the description adds meaningful semantics. It clarifies that entity_slug comes from particle_entity_resolve, episode entity listings, or mention payloads, and gives concrete examples ('germany', 'bitcoin'). For output_format, it goes beyond the enum values by explaining when to use JSON ('only for programmatic chaining where exact field extraction matters') and why markdown is the default for LLM reading. This is valuable guidance the schema alone does not provide.

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 opening sentence states a specific verb and resource: this tool returns a knowledge-graph entity's profile with name, kind, description, and Wikipedia link. It explicitly distinguishes itself from sibling tools by noting it is not the full person/company profile tool and that it is for confirming slugs from particle_entity_resolve. Even without reading the schema, an agent knows exactly what this tool does and how it differs from the person/company getters.

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?

The description gives explicit when-to-use guidance: 'Use it to confirm what a slug from particle_entity_resolve actually refers to' and then lists the long-tail entity categories. It also provides a clear when-not-to-use rule: for linked persons/companies, prefer particle_person_get / particle_company_get, which return full profiles. It closes with downstream usage, telling the agent that entity slugs feed mention, timeseries, and alert tools, making the tool's place in the workflow unambiguous.

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