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

Annotations already declare readOnly, non-destructive and open-world, so the safety and external-network profile is covered. The description adds substantial behavior beyond that: which external corpora are searched per kind, the cap of k results, that each result carries title and licence, that SVG text is returned inline while photos yield download/page links, and that a credit line appears only when the licence demands it — effectively standing in for the absent output schema. It stops short of describing empty-result or error 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 dense sentence plus a return-value sentence; the usage trigger is front-loaded and no clause is pure filler. It is slightly run-on, packing providers, return shape and credit behavior into one long clause, but no sentence is wasted.

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 three-parameter read tool with no output schema, the definition covers when to call it, what corpora back each kind, how many results come back, and the exact return payload including inline SVG versus photo links and conditional credit lines. Nothing essential to correct invocation or result interpretation is missing.

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% and the schema itself explains k, kind and query, so the baseline is 3. The description goes further by binding each kind value to a distinct provider set and licence regime (public-domain logos vs permissive icons vs CC0/CC BY photos), which is real added meaning about what a kind choice implies for licensing.

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?

States a specific verb and resource ('source a logo, icon or photo for an image slot') and names the exact source corpus for each kind (Wikimedia Commons, Simple Icons, Iconify, Openverse), so an agent knows precisely what this retrieves. It also ties itself to the deck-building flow via get_playbook, separating it from retrieval siblings like find_references.

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?

Gives a clear trigger condition ('Use while building an approved slide to source ... for an image slot') and points to get_playbook for context. It does not state exclusions or contrast itself with find_references / get_reference, so the agent must infer that those are for textual references rather than assets.

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