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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: what each result carries (audience, guest and sponsor signals, has_email), that guest_episodes/sponsor_episodes are counted within analyzed_episodes, and that grepfm_url mirrors the search in the app for browsing and export.

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 capability and its filter families are front-loaded, then result contents, then cross-tool and ranking caveats — a sensible order for a 37-parameter tool. The filter enumeration in the first sentence is dense but earns its length; the 'podcast_link' instruction is the one sentence that feels out of place since that parameter is not in the schema.

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?

Given 37 optional parameters, 100% schema coverage, annotations covering safety and no output schema, the description supplies what the structured fields cannot: what a result row contains and where the email addresses actually live. The only gap is that it mentions a podcast_link parameter absent from the input schema, and it does not touch on result volume or pagination (though the schema covers the 200-result cap).

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 relational meaning the schema cannot: search_by guests/sponsors turns the keyword into a person-or-brand lookup, and has_email is only a flag while the actual addresses require get_podcast_contacts. It also explains the default ranking that applies when keyword and order_by are both omitted.

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 and resource plus scale ('Search Grep.FM's database of 3M+ podcasts') and enumerates the filter families it supports, so an agent knows exactly what capability this is. It does not explicitly contrast itself with nearby siblings such as lookup_podcasts, find_similar_podcasts or search_episodes, leaving that differentiation to inference.

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 real routing guidance: emails 'come from get_podcast_contacts', guests/sponsors use 'search_by guests or sponsors', and results default to a quality ranking when no keyword or order_by is given. However, the description never states when this tool should be preferred over lookup_podcasts or find_similar_podcasts, and gives no exclusions or preconditions.

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